Rendered at 20:31:17 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
Greenpants 2 hours ago [-]
I have! I care about data privacy and LLMs being free. I'm using the Pi coding harness but containerized and sandboxed, to make sure it's running completely offline. On my Mac Studio with 128GB RAM (or MacBook with 36GB RAM) I'm using Qwen3.6 35b, with only 3b active parameters so that it runs really fast. I've done a complete redesign for my website's homepage and blog with Django + Wagtail. The latter is interesting, because Wagtail is a bit less well-known, so the agent, without giving it internet access, doesn't always know how to develop for Wagtail. I've used Qwen3.5 122b for when things get more complex. At 10b active parameters, it's significantly slower though.
I've noticed a few things compared to large models like Claude. For starters, you really need to know what you're asking, and be precise; it doesn't do much thinking for you. Any assumptions left open, and it'll take the easiest route to reach the goal (e.g. CSS in HTML), often not the best in terms of architecture.
It gets into loops quite often, and surprisingly often gets the edit tool call wrong, after which it will spend lots of thinking tokens and re-read files instead of retrying (despite the system prompt suggesting so).
Comparing agentic Qwen3.6 35b to Claude Opus is like a junior with knowledge across the board, that you really need to guide, versus a senior that thinks with you on architecture. If Opus gives a 15x speedup, local and fully offline Qwen gives a 5x speedup. Which, given that it's completely free, is still mind-boggling to me :)
lambda 1 hours ago [-]
This is very similar to my setup. Pi in a container (I do let it have network access, just no access to creds or anything, only the one directory that I'm working on at the time and my ~/.pi directory), talking to llama.cpp in another container. I'm on a Strix Halo 128 GiB unified memory laptop.
I've never used the frontier models in earnest, I don't believe in using proprietary tools for my programming, so I can't really compare.
And I'm still a AI skeptic, so I'm doing more testing and kicking the tires than I am actually using it. That means I spend a lot of time trying to break various models, probe them for strengths and weaknesses, etc.
But I find that when I do try to use it for real for agentic coding, Qwen 3.6 35B-A3B is definitely the one I reach for the most often.
For other chat tasks and translation, I'll frequently use Gemma 4 31B.
For audio, I'll use Gemma 4 12B.
I keep a bunch of other models around to try out every once in a while (Qwen 3.5 122B-A10B, Qwen 3.6 27B, Nemotron 3 Super 122B-A12B, Step 3.7 Flash and Minimax M2.7 both at somewhat more aggressive quants, and GPT-OSS 120B if I want super fast but not terribly smart), but so far Qwen 3.6 35B-A3B is really the sweet spot for coding on a setup like this.
chakspak 1 hours ago [-]
Hopefully this isn't off-topic, but your setup sounds just like mine, Strix Halo and (I'm assuming) llama.cpp on ROCm, and I'm finding that the Qwen hybrid models don't handle prompt caching and instead re-process the context in full on every turn. I'm wondering if you were able to solve this and how?
lambda 56 minutes ago [-]
I use Vulkan mostly instead of ROCm. Vulkan is actually a bit faster, paradoxically. I do switch out and try them both out, and it's not a huge difference, but I've been mostly saying on Vulkan.
The re-processing context every turn problem is definitely something I've hit. Some of the causes have been solved upstream in llama.cpp; make sure you're up to date.
But another cause of the issue that has a big effect is that older Qwen models didn't support preserving thinking. This means that each time you have a long sequence of tool calls with interleaved thinkging, as soon as you had your next turn in the chat, it would have to re-process all of that as it would drop all of the reasoning.
Qwen 3.6, however, now supports preserving thinking. This can use a bit more context, becasue you're not dropping the thinking every turn, but it re-uses the cache better, not causing you to have to reprocess a whole turn at a time each time.
In my models.ini, I have this for the Qwen3.6 models:
There are still occasional issues I hit where it will have to re-process, but getting up to date and enabling preserve_thinking has helped a ton.
ndom91 39 minutes ago [-]
+1 using llama.cpp Vulkan releases with the Qwen models - runs much better than the ROCm releases.
I'll have to give the preserve_thinking a shot.
LoganDark 19 minutes ago [-]
What harness are you using? Some of them (e.g. OpenCode) mutate the system prompt every turn, and therefore can't work with a KV cache.
I've had the best luck with Pi so far, but it comes without some bells and whistles you might be used to (e.g. plan mode, subagents, MCP client support)
adyavanapalli 1 hours ago [-]
For the edit tool, you should consider implementing a hash-based approach where each line of code is hashed and referenced by it when doing replacements. You can read up on the approach here: https://blog.can.ac/2026/02/12/the-harness-problem/
I didn't do much benchmarking, but anecdotally, I found it to be making less edit errors. YMMV
ltononro 45 minutes ago [-]
What kind of coding do you do?
Do you keep track of frontier models to vibe check the differences and re-evaluate constantly or are you ok with having a nerfed model forever?
(not being judmental, just really wanto to know your framework here)
Greenpants 30 minutes ago [-]
Some of the work I do, I do for an (EU) organisation that doesn't have clear rules or guidelines on the use of AI yet. Though I have seen colleague-developers blatantly putting source code into external Claude-like models, I stay true to my principles and don't. I know for certain that everything that I run through my local, offline Pi Container Sandbox cannot leave the machine, and thus can't result in a data breach. I do this for the peace of mind.
I do (unscientifically) experiment whenever a new capable local LLM (<=130b) releases with a license that permits commercial use. As for knowing my models require more work than Opus, I don't mind still having to puzzle on getting the architecture right. In any case, it forces me to stay in the loop of what's being built, which is a good thing.
electronsoup 56 minutes ago [-]
> It gets into loops quite often, and surprisingly often gets the edit tool call wrong
I find that running better quantization, like Q8 tend to prevent this even though its a bit slower to run, it saves overall time with less churn
Using 3.6-27b is even slower again than 3.6-35b, but I find the accuracy really pays off
0xbadcafebee 2 hours ago [-]
The harness and the LLM parameters are pretty essential to getting better results and reducing loops. Tweak the parameters and you can mostly eliminate loops without negatively affecting performance (it's a bit complex but ask a SOTA AI to guide you and it's not hard). The harness should also react more intelligently to failures; it can do things like return additional context or hints as it tracks error rates and avg duration of calls. Pi can be easily extended, and it's suggested by the author you modify it to perform better for your use case.
nyxtom 16 minutes ago [-]
Have you found that being much more spec driven helps guide it better?
jmuguy 1 hours ago [-]
Given your knowledge on this - do you think we'll see an open source model with Opus levels of capability? IMO if/when this happens - I would 100% stop using Anthropic.
lambda 1 hours ago [-]
If you believe the benchmarks, Qwen 3.6 35B-A3B already outperforms Claude 4 Opus.
Now, there's a bit of a degree to which some of the open source models do some benchmaxxing, and bigger models with more params may always feel like they have more depth. But anyhow, right now you have something that is arguably comparable to Claude 4 Opus on your laptop. I can't really compare myself because I never used it. It looks like Claude 4 Opus is still available on OpenRouter, so you could try it out and compare yourself if you're interested.
It will likely always be the case that there are proprietary cloud models that are more powerful than what you can run on a laptop. You can just do a whole lot more with terabytes of VRAM on multi-GPU clusters than you can do on a laptop. So for folks who must have the most capable, you're probably not going to want to leave Anthropic.
But right now, the models you can run on your laptop are comparable to the cloud models that were popular when vibecoding and Claude Code first took off.
MrScruff 50 minutes ago [-]
You really need to take the benchmarks with a massive pinch of salt. I’ve been testing local LLMs since the original llama and there’s nothing I’ve tried that is in the same category as Opus.
lambda 43 minutes ago [-]
Which Opus? They certainly outperform Claude 3 Opus.
Anyhow, feel free to try them out head to head on OpenRouter. I'd love to see someone write up their results, of a modern local sized open source model vs. frontier models from ~a year ago, on something other than the standard benchmarks.
MrScruff 34 minutes ago [-]
I’m normally comparing frontier open/cheap models against frontier closed source. I use deepseek/glm regularly, they’re fine and you can get real work done with them but it’s super obvious when you switch back to opus or even sonnet. A 3B active param MoE model is not comparable.
Greenpants 1 hours ago [-]
Let me put it like this. I started with local LLMs when ChatGPT still used GPT-3.5. I was amazed how my MacBook with 8GB RAM could run openhermes2.5-mistral: a 7b parameter model that could generate short stories that sort of made sense. Incredible!
Two years later, and I'm running Qwen3.6 35b agentically to develop the start of a repository and automatically run tests to then improve on itself. I never thought we'd get here so quickly with LLMs back then.
I'm pretty sure in two years we'll have current Opus-like quality in the 30-100b parameter model range. But at that point, Opus 6.3 will reason along for us so much better still, that we'll still look at those models in awe. It's great to look ahead, but let's not forget to appreciate how effective the current local models already are :)
jmuguy 1 hours ago [-]
Haha well I ask because I don't really want/need anything beyond Opus most of the time. And I'm paranoid that Anthropic is going to be forced to charge the true cost of all this before too long.
Greenpants 25 minutes ago [-]
The other upside of running local LLMs is that there's no cloud provider to suddenly charge more for the same, or even less, model use.
It's personal, but I prefer CapEx over OpEx for this. If you can purchase a device upfront that runs a decent local LLM, you get the peace of mind that your setup won't suddenly change over time and can only get better.
zozbot234 1 hours ago [-]
People can't seem to agree on what "Opus class" even means (the latest Opus is apparently pretty weak) but DeepSeek Pro, Kimi and GLM all are quite capable.
computerex 52 minutes ago [-]
Nothing compares to Opus when it comes to "taste" in web design in my experience. Nothing compares to opus in very difficult HPC/model inference development. I worked on this with opus: https://github.com/computerex/dlgo
OpenAI was offering 2x usage at one point and I still used opus just because it's so much more effective.
rvnx 55 minutes ago [-]
To me totally yes, even further, if they keep their existing route, over time people will stop using Anthropic.
More and more specialized and ultra-performant chips are going to flood the consumer market. Especially once new hardware foundries will start producing (well if we don't die from WW3 in the interval).
In 10 years from now, when even basic computers will have 128 GB of memory, and phones will have super optimized tuned models, then what will be the point of Anthropic ?
Just use Gemma/Gemini/Siri or whatever.
Pornography and uncensored models is also pushing toward local models.
It's not like needs of people grows exponentially, the needs follow an asymptote instead (they are capped).
The real revolution is offline robots and self-driving cars, but LLMs are already quite maxed.
For programmers, now, what Anthropic offers is like 3% improvement on a known test (like this pelican riding a bicycle), or on questions leaked from benchmark insiders.
It's ok but not like revolutionary (Fable was better but it was unusable, easy 20 minutes per one prompt due to overthinking).
hparadiz 56 minutes ago [-]
I am right there with you. Mind-boggling. It's a indistinguishable from magic technology!! I tried running some basic tasks through Qwen with Opencode on a 10 year old dual Xeon server for shits and giggles. I gave it a simple task like "use ffprobe first but convert this webm to mp4" and it was able to complete the task with zero network calls outside my network. On 10 year old hardware. It took about 3 minutes to complete the task. Now you may be saying 3 minutes? pfft. But I dare you to do it yourself. You're gonna be googling the CLI switches for at least 10 minutes and setting up your command. I had it actually optimize all the switches on the fly for me based on an initial ffprobe to see what is optimal.
motbus3 34 minutes ago [-]
Try deepseek V4 flash
GardenLetter27 2 hours ago [-]
Could the harness not check for a failed tool call and pass it to a small model for correction without clogging up the main context?
lambda 1 hours ago [-]
The thing is, to do a proper fix it would really need all of the context (maybe the tool call that failed was for an edit to a file that was last touched way at the beginning of the context), so you'd need to either keep that smaller model running doing prompt processing all the time, or have a very long wait while it does prompt processing on your whole session.
And then also, sometimes the tool call errors are because of something like a file was changed out from under it; the larger model is probably going to do a better job of figuring that out and fixing it up.
Finally, in Pi, you can always just use the /tree command to skip back to before a series of failed tool calls, with a summary if you want to let the model know what happened. The Pi /tree command is pretty powerful in managing your context
Greenpants 2 hours ago [-]
I'm actually quite sure that directly retrying the tool call would often fix the edit-call already. But these models have been trained to "think" for a while for any problem solving, so they'll presume the problem of the edit is more fundamental and spend unnecessary tokens filling up the context.
I'll experiment more with the effectiveness of AGENTS.md rules for local Pi agents. I feel like smaller (local) LLMs just lack in attentiveness to elements in the context window, like precise instructions, compared to e.g. Claude models.
amelius 36 minutes ago [-]
Sounds super cool, don't get me wrong, but I suppose for most people the bar is higher than HTML/CSS.
yieldcrv 28 minutes ago [-]
> It gets into loops quite often
matches my experience and a deal breaker
also the context window sizes are too low. I can't operate in 65,000 windows any more because even just reading the code's file structure overruns it and gets me nowhere. Definitely its own art form.
200k context windows and above for me now
I saw a paper last night that should help this a lot though
Greenpants 19 minutes ago [-]
I get that it's a deal breaker to some; it definitely requires patience.
In Pi, /new is my best friend and most-used command for sure. For simple tasks (I decompose complex ones anyway since I don't trust small local LLMs to do this for me), the model doesn't need much context, given that I'm proficient in my codebase myself: "I'd like Feature X. Look into files 1, 2 and 3 to make your edits."
kennywinker 14 minutes ago [-]
Qwen3.6-35b handles 256k context fine if you’ve got room for it. I’m running it with 128k context with just 16gb vram.
nobody_r_knows 1 hours ago [-]
[dead]
horsawlarway 3 hours ago [-]
For personal use, yes.
I replaced a $100/m subscription to claude in favor of running pi harness pointed at unsloth studio, using both qwen (unsloth/Qwen3.6-35B-A3B-MTP-GGUF) and gemma (unsloth/gemma-4-26B-A4B-it-GGUF) models, depending on my mood.
I have a machine I built about 5 years ago with dual RTX3090s in it (I was going to build a new gaming machine anyways, and the llama release had just dropped so I tacked another used 3090 onto the build), and I get ~150tok/s on either of those models (at UD-Q4_K_XL quant) and can use the entire 300k context length without having to exit VRAM.
To be very clear - it's not as good as claude. But it's free and not so much worse that it matters significantly.
For my personal needs, free beats $100/m.
I also have an openclaw instance pointed at the same inference server, and it's great for that (genuinely solid use-case for local models).
Some example projects
- Replacement launcher for android tvs (with usage monitoring and tracking for kids)
- Custom admin portals for my k8s cluster services
- Custom home assistant integrations/automations (recently some shelly devices for power monitoring and switching)
- Grocery list management and meal planning (mostly via openclaw)
- some custom workflows for 3d asset generation in comfyui.
---
Long story short, if you're trying to make money via software... I'd probably still recommend using a paid provider. But the local models are very capable of cool stuff.
rootlocus 2 hours ago [-]
2x RTX3090 are around $4400. Without any electricity costs or other parts, that's 3.6 years of $100/m claude.
overgard 34 minutes ago [-]
Assuming the $100/m claude subscription is still around in three years.
freetonik 2 hours ago [-]
That's also years of top tier PC gaming, if you're into that.
augusto-moura 2 hours ago [-]
2x RTX3090 is extremely overkill for gaming, you can run any released game on earth on ultra for much less
drnick1 52 minutes ago [-]
1x RTX3090 is absolutely not overkill for gaming however. Nowadays it's barely enough to get 60FPS in 4K in some recently released games. But the shocking part is that my 3090 is still probably worth as much as when I bought it about 4 years ago.
overgard 33 minutes ago [-]
Having a second card doesn't really work well for gaming.
googletron 1 hours ago [-]
what?
kakacik 1 hours ago [-]
AFAIK nvidia cards dont work in tandem (aka sli in the past) very well these days. So that aint true.
Also, 2 gens old means bad performance at ray tracing, abysmal path tracing if at all. Pretty sure it can't run smoothly CP2077 in native 4k without dlss upscalers with all on ultra.
himata4113 1 hours ago [-]
You can have the 2nd card as an offload for upscaling, frame generation and whatnot.
irishcoffee 20 minutes ago [-]
When I'm not running models I use the 2nd one in a pass-thru configuration to a windows vm for various things, usually gaming.
jmuguy 1 hours ago [-]
Or a really excellent experience playing Satisfactory with the settings cranked up, which is priceless.
horsawlarway 2 hours ago [-]
Yes, today is not a great time to purchase hardware.
When I bought, I paid $850 a piece. And I needed one anyways for the gaming I was going to do.
My guess is the next good time to buy is going to be 24-36 months from now, depending on how the AI bubble goes.
---
I'll add to this, I personally don't like Apple hardware (not so much related to the hardware as their company philosophy) but their machines with unified memory (or AMDs latest unified memory offerings) get pretty equivalent speeds to my 3090s, and are probably a much better modern entrypoint to local llms.
There's a reason the joke is that Silicon Valley software devs bought up all the Mac minis for OpenClaw.
You can get a 48gb unified RAM M4 pro mac mini for ~2k. If you're not going to do much else with the machine, it's what I'd pick as my budget inference device right now. Spend a year of claude now, get ~150tok/s for the next decade (plus) for ~free.
If you want more capable and are willing to spend a little more, go with the newer Ryzen AI Max+ 395 machines.
You'll spend less on power too.
My last suggestion would be to go buy an RTX3090 at this point. You can do a lot better for a lot cheaper.
tripleee 1 hours ago [-]
Christ GPU prices have gotten crazy
How do AMD cards perform with LLMs? A 9070 is sold for ~$600 and has 16GB VRAM
overgard 30 minutes ago [-]
In my personal experience, I wouldn't bother with 16GB cards for coding -- the useful models are _slightly_ too large to work at any reasonable speed
lambda 50 minutes ago [-]
That should do pretty well. Memory bandwidth is the biggest bottleneck for token generation, at 644 GB/s you should be able to do pretty well on a 9070, while prompt proessing is more compute bound and Nvidia tends to have the edge there.
16 GiB won't fit you much, so you'd probably want at least 2x, and preferably 3x of those, and then you need a motherboard, power, etc. that can handle that.
nyrikki 2 hours ago [-]
You can get 60tps with three 1080tis and the sparse model, and I bet two 16gb 5060tis would do the same for ~1200. One 3090 is enough for a useful system, even on an old am4 host.
flowerthoughts 1 hours ago [-]
In 3.6 years, chances are they are still worth $3k. Unless some new chip fab pops up that can spam the chip market. Even if the AI bubble bursts, I doubt we'll see high-RAM GPUs sell off.
sieabahlpark 2 hours ago [-]
[dead]
kpw94 2 hours ago [-]
> gemma (unsloth/gemma-4-26B-A4B-it-GGUF) models
Since you're running quantized (at UD-Q4_K_XL) , check out the "qat" models (unsloth/gemma-4-26B-A4B-it-qat-GGUF) !
> Quantization-Aware Training (QAT) [...] allows preserving similar quality to bfloat16 while dramatically reducing the memory requirements to load the model
twothreeone 2 hours ago [-]
> unsloth/Qwen3.6-35B-A3B-MTP-GGUF
I've actually tried this exact same model locally as well.. albeit on just a single 3090 at 128k context and I got around 40-60tok/s with Q4_K quantization.
The thing that bugged me the most was really the quality of the output on moderately complex real-world coding tasks. Having to switch between "prompt/vibe" and "manually implement" is such a big context switch burden, because you really have to ask yourself every few minutes if you're "holding it wrong" or the model is just too stupid.
It also doesn't really seem to handle transitions from "low-level implementation detail" to "high-level design" well, e.g., it wouldn't easily render tables and such. With Claude I don't have this issue.. so I think for now my verdict would be that it's not really a viable replacement. I really hope it will be in a few months time.
Oh and I used "aider" to replace claude CLI, which maybe that's also sub-optimal.. I'm not sure. The MCP marketplaces are useful of course, though arguably you could just manually replace them over time.
horsawlarway 1 hours ago [-]
I don't generally switch to implementing myself on the model, although there are definitely times where I stop it and correct it mid-task.
It's prone to thinking longer and more repetitively, again - it's definitely not opus 4.7/4.8.
I've been using pi.dev as my harness for it, and been pleasantly surprised by how nice it feels (I have used aider, but only very briefly and quite a while back - so I can't realistically compare).
I would say it's roughly where I felt claude was a year back - Most of the sessions need to be more "pair programming" and less "I let it run for hours".
I'm a big fan of frequent "human in the loop" style workflows even when I'm on something like opus at work, though. I have opinions about lots of things, and re-inforcing that the model should stop and ask frequently seems to get me considerably better output, without having to "re-roll" if you will.
I've done a good bit of management, and I think it's roughly producing what a junior dev might produce in a day every 5 minutes. And just like a junior dev, you need to be steering it back on track fairly often.
Opus feels more like a mid-level at this point. I can hand it a chunk of work and "leave" but I still get better output if I'm checked-in and watching/steering.
unethical_ban 33 minutes ago [-]
I'm so out of the loop on this stuff, it's the first time in my IT career I feel really behind on things.
I've used Claude Opus to quickly and effectively pound out some 100-200 line scripts that integrate with a vendor's API, and it one-shotted them both almost perfectly.
I wonder if for a lot of these local models, the scope of the AI assistance should simply be smaller: You architect the tools and the function definitions, and then tell AI to implement one at a time? Does anyone do that rigorously?
gonzalohm 2 hours ago [-]
Did you double the tokens per second by adding a second GPU or was the increase significantly less?
horsawlarway 2 hours ago [-]
No real change in inference speed. It basically just allows me to slot in more context or a bigger model.
A single RTX-3090 will do approximately the same tok/s, but it won't fit the entire 300k context in VRAM.
Sometimes that matters, a lot of times it doesn't.
On the speed front - MOE models are great. Biggest perf difference in modern models is the move to MOE architectures.
I get very similar quality from the both the Gemma-4 31B dense model, and the Gemma-4 26B MOE model (both at Q4 quant) but the MOE version runs at ~3 times the speed (150tok/s vs 46tok/s).
mirekrusin 2 hours ago [-]
You’re adding extra gpu for more vram, not speed.
agup792 2 hours ago [-]
That sounds amazing. If I had some GPUs sitting around, I would totally do it. Sounds expensive to do it otherwise though.
bluejay2387 2 hours ago [-]
About 90% of my coding is on Qwen 3.6 27b and Open Code with some custom skills and Semble. It is NOT as smart as CC or Codex but its enough to get most of my work done. I didn't set out to replace CC and Codex (I have an RTX 6000 so the TPS is faster than I care about, but the RTX 6000 was originally for other work). I only tried this just to see how close you could get to a frontier model for coding as an experiment, but it was good enough that I stuck with it. I still fall back to Codex for really complicated stuff and to polish UI's as that seems to be the weakest element to working in Qwen.This isn't a recommendation because I don't think most people have an RTX 6000 laying around and the cost would be many years of MAX CC or Codex subscriptions, but at least this seems possible. Maybe in a few more years it will even be practical.
Other Notes: I have had to set the compact target to 75% on a 256k context window as once the conversation length goes about 100k I start seeing a drop in the quality and speed. This becomes very problematic after about 150k. I tried Qwen 3.5 122b too but it actually seems much worse at coding than 3.6 27b even though its much larger. Maybe because I am using a 4bit quant or maybe I just don't have it configured correctly? I know 3.6 is newer but I didn't expect it to out perform a model that is much larger from the prior generation. Gemma 4 31b is a good model for other tasks but at least my personal experience is that Qwen outperforms in coding. Nemotron Super 120b is great at a lot of stuff but it also seems to be not as good at coding as Qwen. This was very surprising to me.
heipei 2 hours ago [-]
Same here, I use Qwen 3.6 27b (Q6 quant) with llama.cpp on an RTX 5090 using the pi agent exclusively now. The fact that it's local means that I never have to think about token pricing, quotas, time of day, or data sensitivity. I have limited the GPU from 600W to 450W which means the system stays whisper quiet during inference.
I have become so "lazy" (in a good way), so far that I've started using the model for lots of daily mundane things on top of just coding:
* "commit this on a branch, push, create a PR and assign $nickname for review"
* "Use the Stripe CLI to download all open and overdue invoices and reconcile them with this CSV export from our bank account."
* "Use these Elasticsearch credentials to summarise what kind of operations are causing load at the moment."
* "Tell me if our codebase already supports X and where it's implemented."
bo1024 2 hours ago [-]
Qwen3.5-122B is actually Qwen3.5-122B-A10B. The A10B means that this is a "mixture of experts" model where only 10B parameters are activated at a given time. Whereas Qwen3.6-27B is a "dense" model where all 27B parameters are activated all the time. So for many tasks, you'd expect the 27B dense model to be better than the 122B-A10B model.
htrp 2 hours ago [-]
why 27b vs 35b? Is MoE that much worse for coding?
electronsoup 51 minutes ago [-]
Yeah MoE is a little worse for the same size, but you can often run bigger MoEs at respectable speeds even on cpu ram offload. The dense models really need to be 100% vram
pierotofy 3 hours ago [-]
Yes. Llama.cpp + Qwen3.6-35b (MTP) + OpenCode is quite capable and runs on a single RTX 3090 and is faster than most cloud models. Quality is like running edge models from 8-12 months ago. Setup details at https://github.com/pierotofy/LocalCodingLLM/
jacobgold 3 hours ago [-]
"Quality is like running edge models from 8-12 months ago."
That sounds great for hobbyists but IMHO it wasn't until Opus 4.6 was released six months go (Dec 25, 2025) that we had a model good enough for professionals to use as a primary driver of their coding agents. That seems to be the threshold worth aiming for.
sbrother 2 hours ago [-]
I strongly agree on that being the release where these tools got good enough to substantially speed up my professional work. I have to admit I was super skeptical of AI coding until then.
dnautics 2 hours ago [-]
for me (might be because of the language im using) i had a substantial bump around september and a huge bump around January.
in my stuff now i use an OT library that claude put finishing touches on in September.
Projectiboga 2 hours ago [-]
So thalen it might be 6-8 months to get to useable on a local open model? Of course state of the art will be a year ahead, a generation at the current pace.
pierotofy 3 hours ago [-]
I use it for work.
jacobgold 2 hours ago [-]
That's cool if you prefer it, but it is hard to imagine it being a strictly rational choice when much better quality is available at a price that is small relative to the cost of an employee. Or is there something specific about your use-case?
vector_spaces 2 hours ago [-]
Not all work requires every facet to be so sharply optimized, and there may be other constraints that are completely invisible to you. Some that were easy for me to imagine: the parent works in a heavily regulated industry, their IT team is slow-moving and paranoid and this is a safe, under-the-radar workaround, the output is "good enough" for their purposes and they find tinkering with it to be fun.
Regardless I don't think it's fruitful to be so condescending with such little insight into this person's situation. Even if you had total insight -- let people be and withhold your judgement, or at least keep it to yourself. Making people feel stupid is a great way to turn people off to pretty much anything else you have to say
lokar 2 hours ago [-]
Won’t it depend on what you use it for? A less capable system might be fine for boilerplate, moderate re-factoring, etc. Not everyone is building whole features in one go.
pierotofy 2 hours ago [-]
To me, what's not rational is believing you must rent the tools of your trade while exposing all of your employer's intellectual property to a third party. Difference of opinion.
jacobgold 1 hours ago [-]
It's not my opinion that you "must" rent tools but it certainly is the pragmatic choice in 2026. I would be as happy as anyone for this situation to change and I expect it to at some point.
trueno 2 hours ago [-]
i have a 128gb m4 max macbook pro i've been wanting to tinker with this stuff but genuinely never find the time. any mac users in here running similar to the above that can share their experience?
i always see great debates with local stuff but the space is constantly moving goalposts and all the vernacular is pretty unfamiliar to me. i'd love to understand what people with objective experience feel they've traded away (or gained) when going local so i can determine for myself if these things are a good fit.
brycesub 2 hours ago [-]
If you have a 128GB Mac you really ought to try out: https://github.com/antirez/ds4 by the creator of redis. This is probably as close to it gets to state-of-the-art local LLM + agentic coding.
lostlogin 1 hours ago [-]
Thank you.
htrp 2 hours ago [-]
Use your ClaudeCode sub and tell it to set it up for you
atomicnumber3 3 hours ago [-]
Same. I have no desire to use Claude at all anymore.
pierotofy 3 hours ago [-]
Yep. Screw Anthropic, CloseAI and all other rent seekers in this space.
akulbe 1 hours ago [-]
I have an M2 Max MBP with 96GB of RAM. What models and setup would you use for this kind of configuration?
monirmamoun 6 minutes ago [-]
download LM Studio to play with, and it will let you search for models... try Qwen3.6-35B-A3B at 4,5 or 6 bits (6 bit XL is near perfect) and use pi coder or another harness to access it... you can also try Unsloth studio and try same model to start. LM Studio slighter easier to use, Unsloth probably better quality. Neither one is super great quality by the way (meaning: they crash or act weirdly too often to be full production solutions, but can work for local coding). ONCE YOU DOWNLOAD EITHER APP... it will let you search huggingface for the models. Just type qwen to start looking and ... start messing around. And you connect the pi coder harness using the http interface that LM Studio and Unsloth offer to the engine API, so make sure you figure out that url and turn it on... something like 127.0.0.1:1234/api would be a typical IP (localhost) and port (1234 is used by LM Studio)
daveidol 2 hours ago [-]
Do you do your dev work on the windows machine (referenced in the docs), or do you remotely access it from a separate machine? I ask because I have a RTX 3090 kicking around in a gaming desktop, but I don't use it for any dev work (I use a Macbook Pro).
snake_n_my_boot 11 minutes ago [-]
I have a similar set up and have been using it to learn and tinker with open models. I run Ollama on the gaming desktop and point OpenCode to it from my MacBook. Works nicely for me so far.
lelandbatey 3 hours ago [-]
I use it, it's good, I get work done, but know that they really mean it when they say
> "Quality is like running edge models from 8-12 months ago"
Don't expect Opus, expect more like Haiku. If you micromanage it, you'll get great results. If you want it to be a human in a box, it'll flounder.
dheera 2 hours ago [-]
Am I doing something wrong or has ollama become shittified?
I'm looking at https://ollama.com/search and the top few models like kimi-k2.7-code say "cloud" and I can't seem to ollama pull them.
I thought the whole POINT of ollama was not-cloud?
> I thought the whole POINT of ollama was not-cloud?
It was at first, then the developers realized they had a massive userbase they could monetize. A tale as old as open source...
satvikpendem 2 hours ago [-]
Ollama is not recommended to be used. Use llama.cpp.
jmorgan 2 hours ago [-]
The larger models are available on Ollama's cloud as most folks don't have the hardware to run 500B-1T parameter models.
toyg 2 hours ago [-]
Yes, you've nailed it. Ollama are desperately trying to pull a Cursor - like 3791 other projects in this space.
dominotw 3 hours ago [-]
how much does the setup cost if i want to buy all the hardware now and increased power costs?
codinhood 3 hours ago [-]
I don't think you're going to get many "true" answers to this. The opportunity cost of not using the latest and best models is just too much right now.
Every month I research this and come to the same conclusion: the time, effort, and cost required to get local models (and the coding tools around them) to perform even close to Claude Code with sonnet/opus just not worth it right now. If it was, it would be distributive enough to be in the news.
Not that I'm discounting someone hasn't already solved this, just trying to Occam razor my way out of diving too deep down rabbit holes.
pyeri 2 hours ago [-]
At some point, there will come a saturation point for that "Opportunity cost FOMO train ride", and I think we are already past that point. Mythos class models are a whole different beasts and cutting edge on reasoning but not much use for the problem domains most developers are trying to solve.
The present Sonnet/Opus versions (~4.8) will likely be what everyone in the enterprise might end up using eventually. And even though local models aren't there yet, there are budget alternatives from the families of DeepSeek, Kimi, GPT, MiniMax, etc. available through APIs of NVidida, OpenRouter, Groq, etc. which are very much Sonnet grade.
codinhood 2 hours ago [-]
Yeah this is exactly what I'm waiting for.
Personally, I don't think we're at that point yet. While I do think model improvement is starting to plateau (reaching a local ceiling), I'm not convinced local models are as good as sonnet/opus yet. The gap is still too much. But I'm excited for those models to reach those levels.
mark_l_watson 53 minutes ago [-]
Sounds like a correct conclusion to me also. I am trying to transition to a layered system: local, then OpenCode with commercial vendor APIs for models like DeepSeek v4 flash, then DeepSeek v4 Pro.
With a layered approach we can slowly shift to running more locally and still get required work done. Really, my local setup is so much better than it was 2 months ago, and extremely better than 6 months ago - on the same hardware.
sakopov 2 hours ago [-]
This seems to be the answer. Building a rig with a decent graphics card will cost $2k+ and will produce sub-par results. Might as well milk the $100/m Claude sub until open-source alternatives reach parity with today's frontier models.
MadrasThorn 1 hours ago [-]
It's great at accelerating hardware innovation however.
jrm4 3 hours ago [-]
But you're pretty much measuring opportunity cost in tokens per second, no?
I think it strongly remains to be seen whether e.g. tokens per second (multiplied or whatever by percieved quality of private model) actually means "better or more useful output."
I strongly suspect it does not. (though I also strongly suspect this will be very difficult to measure because the incentive to lie about metrics here will be so strong.)
codinhood 2 hours ago [-]
If you’re arguing that model metrics don’t necessarily translate into useful output, I agree. That’s not how I measure the success of a mode and not really the point I'm trying to make. I try to set things up and test it on my actual projects.
What I’m saying is that if local models were actually comparable to Claude Code in practice, we wouldn’t be having threads like this. It would be obvious to the people using them, and it would be massively disruptive. Why would individuals and companies pay hundreds or thousands for Claude Code if they could run something locally and consistently get similar results?
Every month I revisit the local ecosystem hoping the answer has changed. So far, my experience has been that it hasn’t.
Rastonbury 2 hours ago [-]
I think they are referring to the opportunity cost of time saved on doing things a local model cannot do or fixing it's mistakes against the cost of a subscription
sosodev 3 hours ago [-]
The problem with this question is that it encompasses a huge spectrum of capabilities and expectations. If you can only run an 8B model and expect it to be good at vibe coding / one shotting things you're going to have a bad time.
If you're able to run a model on the scale of ~30B, you can find that with a reasonably scoped and well defined task they do very well. I've found both Gemma4-31B and Qwen3.6-27B to be the best in this range at the moment. You can swap in the MoE models for faster inference, but they are noticeably worse at most tasks. They can one-shot / vibe code tasks with small scope, but still do much better with guidance.
If you really want frontier-like capabilities, you'll probably need at least 128GB of memory and either huge compute or a lot of patience. Most people just don't have either the money or the patience to make these local models work.
The patience required for local model usage goes far beyond just waiting for tokens though. It takes a lot of effort to get things configured and working properly for your workflow and hardware.
argee 3 hours ago [-]
I use Gemma 4 26B A4B on my Macbook (M4 Pro, 48 GB RAM) to study Rust (and ask other myriad questions). I don't trust it to do a good job in an IDE/harness to one-shot anything but the most trivial of changes. Still, it's fast and good enough that it could handle being a "co-pilot" on small to medium context tasks where you've got your hands on the wheel and your eyes on the road — and are driving under the speed limit. That's remarkable given where we were a couple of years ago.
I don't think I'd be using AI to code at all if this weren't the case. (I don't want to feel stunted or stuck just from losing my internet connection.)
garethsprice 35 minutes ago [-]
Using OpenCode + OhMyOpenCode + Qwen 3.6 35B-A3B Q_4_KM on an Ada 4000 (20GB VRAM) at 55 tok/sec for generation (slower than it sounds as OpenCode has a bunch of context it adds). Meaning to check out pi when I get a minute as I hear that one mentioned a lot lately.
I am using Opus to generate plans that the local agent then follows, then validated by Opus. So I'm not at 100% local but these models are increasingly part of my production workflow. Probably not worth doing - yet - unless you are a hobbyist who likes spending time and money tinkering.
This setup is certainly not as "good" as Opus or other frontier models but they are "good enough" for an increasing number of rote tasks. You don't need to drive a Rolls Royce to the supermarket, when a used Corolla gets you there just fine.
It also enables new workflows that would be cost-prohibitive with frontier LLMs (especially as token costs rise) - eg. overnight I use the Chrome devtools MCP and have the above setup fuzz-test as a user for a number of hours and see if it can break things. Even got it working with multi-modal so it can check screenshots, which blows my mind (and not my wallet, as Claude+screenshots burns $$$).
The "12-18 months behind frontier" sounds about right, it's about where I was with gpt-4o and basic harnesses back then. In another 12-18 months my bet is we have Opus-level models that can be run locally for <$5k... but the frontier models will be even further forward (unless governments have blocked them). Fun times.
jodoherty 2 hours ago [-]
I use pi with an RTX Pro 6000 Blackwell to run Gemma 4 31b to do all my agentic coding.
I find it useful.
This side project highlights a similar approach to how I scope and tackle projects at work now:
You have to apply a lot of careful architecture and TDD to your approach. Eliminate technical risk by tackling hard things early and wrapping them up in a simple, easy to use interface.
I find I can get some projects done 2-3 times faster than if I wrote them by hand. It can also save about 5-10x time on mundane or broadly scoped projects by helping me consolidate and try out ideas very quickly.
Setup-wise, I switch between vLLM using nvidia/Gemma-4-31B-IT-NVFP4 and llama.cpp using unsloth/gemma-4-31B-it-qat-GGUF with MTP. I throttle the GPU power usage to 400W.
My current llama.cpp setup gets token generation rates between 60-150 t/s depending on MTP draft acceptance rates. Prefill is between 1500-4000 t/s depending on context length/depth.
redox99 2 hours ago [-]
Models that you can run at home (Like Qwen 35B) aren't remotely close to Opus or GPT 5.5. Not even close. The only open models that are in that neighbor are around 1T params, so forget about running at home.
It's kind of like driving a shitbox. It can often drive you from A to B, and some people will try to convince you it's fine. It's not.
There's no logical reason other than absolutely requiring the privacy, doing it for fun, or niche use cases like airplanes and so on. If you can't spend the insanely subsidized $20 for codex, you can use an API for chinese models which will run circles around these tiny models.
pbasista 2 hours ago [-]
> Models that you can run at home (Like Qwen 35B) aren't remotely close to Opus or GPT 5.5.
Is that characterization based on some objective facts or benchmarks?
kube-system 1 hours ago [-]
Yes, there aren't any 35B models that are beating frontier models at just about anything generalized
redox99 2 hours ago [-]
Based on private test prompts I've run through OpenRouter.
Kostic 3 hours ago [-]
For personal needs I connected VSCode with llama.cpp running Qwen 3.6 27B or Gemma 4 31B and it's good enough to cancel my cloud subscription.
Qwen running on my 1st GPU at q4@176k context from 70 to 50 tok/s with MTP, pretty good for coding.
Gemma on the other hand is using both GPUs, running q8@64k context, doing document sentiment analysis, summarization, proofreading and translating, at consistent 25 tok/s. Somewhat slow but usable for batched workflows. Might get some more once llama.cpp starts supporting MTP with tensor split mode.
Still using frontier LLMs at dayjob since I'm not paying it and those are obviously better. Hopefully we'll have a Sonnet 4.6/Opus 4.5 level 30B model in a year or so.
EDIT: Prompt processing starts from 800 t/s and drops to 400 t/s. In most cases my starting prompts are around 16k-24k of tokens and require from 60 to 90 seconds to be processed. Not great but acceptable.
arjie 4 hours ago [-]
Not “local” and not interactive coding but sharing since it might be helpful. I have 2x RTX Pro 6000 Blackwell running DeepSeek V4 Flash. I get 160 tok/s raw but it’s a reasoning model. For my use case, I have it auto-write code and another system auto-review the code.
I occasionally use it with pi to write some code and it’s blazing fast but it’s mostly habit that keeps me with CC and Codex.
akersten 2 hours ago [-]
> I have 2x RTX Pro 6000 Blackwell
Where did you find/order these? All the sites I can find are either out of stock, only sell to businesses, or are otherwise sketchy...
leptons 3 hours ago [-]
Have you measured your electricity consumption for this rig? I have to wonder how much it would cost you per month.
ux266478 2 hours ago [-]
Not nearly as much as you might think. 1.2kw where I live translates to about $0.12/hr, and that's when running full clip. If you have a decent solar hookup, it's small fraction on a sunny day.
The expensive part is the upfront hardware cost and the electrical system upgrade you'll need to give your house.
jborak 1 hours ago [-]
I'm using 4x RTX 5070's and first-gen AMD threadripper (1950X) to run Qwen3.6 27B (MTP) Q6_K with llama.cpp and it works great as a daily driver with Pi. Around 50-60 toks/sec. I also connect a few other applications to it such as OpenWeb UI and recently set up Bifrost, an LLM gateway, to be the primary access point for the models I serve.
I've tried other models such as Qwen3.6 35B A3B and I've found that 27B works better for me when it comes to coding. It's slower being a dense model but the quality seems much better. Inference on my system for Qwen3.6 35B A3B is around 130-140 toks/sec, non-MTP, which is insanely fast!
You don't need 4x 5070's to run Qwen3.6 27B, three or maybe even two will work. However, I use MTP (multi-token prediction) to speed up 27B and that eats up more memory because the draft model requires its own context.
Another thing to keep in mind is that the tools you're using have their system prompts that are loaded into the model for each conversation. When I fire up Pi, working with the model is very snappy at start. When I interact with the LLM via Hermes CLI, it's much slower. That's because each prompt with Hermes is loading so much stuff (skills, tools, etc.) into the context and then it's there forever until the conversation ends.
I like running models at home for privacy, but I also like how there are no quotas, usage isn't a worry. If the future is "loop engineering" then you will be burning through tokens and $$$ using a cloud models.
My system idles around 200W and is around 350-450W when inference load is high. Decoding (token generation) isn't all that efficient, and your GPUs sit idle more than you think during inference. Advancements like diffusion may 1) speed up decoding and 2) let you utilize more of your idle GPU.
627467 16 minutes ago [-]
So, everyone has different context, but how free is free running these local models? Like having a power hungry machine always on in the cupboard?
How much does this ware out the hardware?
Also, if privacy is the main reason for running local models, why not use venice.ai and equivalent?
cuttysnark 3 hours ago [-]
I've had some success with local models by chaining "agents" together in a workflow. Each agent has a different prompt and uses a different ollama model based on what their role is. The project manager, schema agent(qwen3:14b), etc. doesn't use the same model as the coding agent (qwen2.5-coder:7b). Between each step is an orchestrator and with a Playwright task which attempts to surface errors to the agent who introduced the previous code block. Only error-free blocks are forwarded to the next workflow step.
Probably the biggest improvement was including a backend-for-agents service definition which instructed the schema agent they were to only produce only a manifest based on the task, and to pass off that off to the next agent.
In short, I split tasks up into many pieces by defining a workflow where agents are only allowed to do very specific things before their work is passed along. This keeps them grounded and capable while also creating places for me to intervene if a workflow was say 25% or 90% successful.
sowbug 42 minutes ago [-]
Have you (or anyone else) tried letting agents compete? For example, give the same coding task to two models, or to the same model with a different seed, and have the reviewer choose the better result.
Some think the human brain works similarly: thousands of mini-brain cortical columns, each with a slightly different take on the situation, voting in a majority-rules system.
pianopatrick 2 hours ago [-]
I wish someone would do a benchmark and competition for this kind of work flow so we could figure out what works well.
Like "Here's this consumer grade GPU. Using only this GPU but with whatever models and workflow you want, see how well you can do on xyz benchmark."
Contestants would be given like 1 hour max and scored based on % of questions answered, % of questions correct and total time to finish.
Like "The Local AI challenge"
GodelNumbering 2 hours ago [-]
As someone that spends all day every day talking to LLMs, I'd say the OSS frontier models + a good harness is already a sufficient combo. For local deployments, we are missing one or two hardware generations (and may not get that soon since hardware companies are heavily favoring datacenter segment) to fully move to a local setup.
HappySweeney 4 hours ago [-]
I have an optane and lots of ram, so I tried full-fat models for writing some function overnight, as I get about 0.7 t/s. My current go-to test is to update a scalar function to transpose a bit-matrix to one using avx512. the cloud models all play with that like its nothing. Kimi 2.6 and GLM 5.1 both failed miserably.
stymaar 3 hours ago [-]
Yes, Qwen3.6-35B-A3B on a Strix Halo 128GB (Bosgame M5).
I have way too much VRAM forme such a model but Qwen never released the 122B version of Qwen3.6, which is the best class of model for my hardware. But at the same time my electricity bill is negligible, this is originally a laptop chip and it shows, it consumes almost nothing while idle and a little above 120W during prompt processing.
And Qwen3.6 has been surprisingly effective for me, I still use Clause occasionally but only for like 10% of my needs which allows me to stay well under the quota even with the cheapest plan.
Speed: ~800tps prompt processing and 50tps for token generation (with no speculative decoding).
manmal 2 hours ago [-]
Have you tried the 27B dense version? It’s way better for coding.
anana_ 2 hours ago [-]
Unfortunately on Strix Halo or any similar unified memory set up, dense models are gonna be dirt slow due to the tiny memory bandwidth... But I agree, 27B is superior.
stymaar 1 hours ago [-]
Exactly. That's why I'm disappointed there wasn't a 122B version, it's 27B but for Strix Halo users.
1 hours ago [-]
moezd 2 hours ago [-]
Not yet. Without pure Apple game or decent GPUs, even with a lot of RAM and threads, all you get is about 30-50 tokens/second, and that's thinking turned off. Without these optimizations your model will have a field day with your MCPs, skills and agent descriptions and you will watch the paint dry before seeing the first output token. Local model serving means you have to fight for every token in your context window, which is quite opposite of what Claude/GPT/Copilot are pushing the industry towards.
grmnygrmny2 2 hours ago [-]
Just sharing my $0.02 here - I have ethical objections to using OpenAI or Anthropic products so I was a reluctant adopter of LLMs at all. Local models address most, though not all, my moral objections so I’ve been using them for work and personal projects for about a month.
The hardware I have (32gb Macs and a gaming PC with 10gb 3080) can only get me to Qwen3.6-35B-A3B at various quants but that’s enough (200-400 PP, 20-30 TG).
It’s taken some time to learn how to best utilize it - some things take a bit of babysitting or direction - but it’s quite useful. Not having ever used CC I can’t compare but it’s been a great assistant or pair programmer for everything from embedded C++ to Vue. I wish I could run 27B as there have been moments when this model feels like it just can’t quite figure something out but those moments are quite rare. For a lot of tasks it’s a huge time saver and has proved super capable at digging into and fixing bugs given pretty vague instructions.
I’m using Pi as my harness.
kristianpaul 28 minutes ago [-]
Qwen3.6 35B on gigabyte aitop (spark clone) but be very specif what you ask and how should be solved
Nemotron super 3 110B works well for 1M context long vibecoding sessions
I also use Pi harness with no extension
acc_297 4 hours ago [-]
I've been wondering lately if it would help to take a medium sized model and either in cloud or some local setup actually do Reinforcement Learning from Human Feedback (RLHF) on every prompt as a chore - I don't know if trying to manually finetune a model to your use habits would ruin it or help - ideally if you were diligent you could get rid of some of the ticks that make models for the general public difficult to work with e.g. overly sycophantic, overly verbose, annoying tendency to explain via analogies
but perhaps one individuals prompt feedback just isn't going to ever be enough I'm not sure how much you need (I know people working at big companies that have purchased in-house agents fine-tuned on internal documents etc.. and apparently these end up with bizarre behaviours not necessarily more helpful than the standard models)
I'd like to be able to essentially edit every response given by an agent and then finetune on the difference between what it produced and how I edited the text. Personally I would just remove a lot of the adjectives and try to distill the responses to core responses but I worry based on some of the work done by Owain Evans and other alignment researchers that this can sometimes push agents into tricky-to-predict tendancies.
htrp 1 hours ago [-]
Cursor is doing that (i think with Fireworks as their provider)
I'm interested in trying something similar. I was thinking to do this for my OpenClaw agent.
About Owain Evans work: I think he did SFT. On Twitter someone was saying that RL is not as susceptible to what he showed. I'd like to try that
bijowo1676 2 hours ago [-]
One of the interesting setups I saw is using expensive frontier models to write and update markdown for your app: specs, product requirements, architecture, etc
but then use cheap/local model to implement the specs.
Markdown is more effective at compressing information and fits the context window easier, than hundreds of source code files
but this requires second and third passes, to smooth out the rough edges
has anyone tried that?
bravetraveler 2 hours ago [-]
I'm largely 'all natural', any of my little LLM usage is local. 128G Strix system, a not-super-dense Qwen or Gemma variant will get 50-80 tok/s output. Not subscribing to Anthropic/OpenAI/etc even in the unlikely event these are the last local models released; simply not needed. Entirely fine without and in-model tool usage covers my currency concerns.
Results depend on the model, of course, and your computer is the limit. Mine wasn't up to the task, unfortunately.
overgard 36 minutes ago [-]
I haven't yet, but I just bought a 128GB M5 Max 40 core which I'm hoping can do it (if not, it's a good laptop regardless, I actually need that amount of RAM for non-LLM stuff)
ndom91 1 hours ago [-]
Not 100%, I still fall back to Claude for most day-job stuff. But I've been trying to use Qwen 3.6 and Gemma 4 on my framework desktop mainboard (Strix Halo) as much as possible.
I've been working on an ops style tool for local LLM inference. Proxying, api keys, request logging, model rewriting and much much more.
Pretty good results with qwen 3.6 27b dense. I’d say it’s about equal to (Claude) haiku 4.5 maybe sonnet depending on the task.
kadoban 3 hours ago [-]
What tool do you use to drive things for you, out of curiosity?
kandros 4 hours ago [-]
I’d rather ask my butcher than Haiku for coding tasks
papichulo4 2 hours ago [-]
Agreed on this. Anthropic has now changed the verbiage on the definitions of the models under `/model` to say that Opus is for everyday usage, and Sonnet is for routine tasks.
There's apparently a reason Sonnet and Haiku have been left in previous version #s.
Still encouraging, though, that things are catching up. We can't expect $20k local setups to match $20bn compute clusters.
1 hours ago [-]
blurbleblurble 3 hours ago [-]
My experience is that it's not the models themselves that are limiting right now, it's the clunky alternative harnesses with weird missing features making for bad ergonomics around stuff like queue management, interruption, subagents, goals, etc.
coder543 1 hours ago [-]
I agree completely.
It's also annoying that OpenCode doesn't even try to support local LLMs properly.
Getting OpenCode to work is possible, but extremely manual and clunky to configure. I have written a script to automate converting my llama-server configs into an OpenCode config, and that helps, but it's not ideal.
I have seriously considered writing Yet Another Coding Harness in my free time. I have some ideas for what would make it nice.
horsawlarway 3 hours ago [-]
Pi is decent.
I've used the cli agents for claude, cursor, and pi, plus several custom harnesses I've written myself from time to time as experiments (and I guess technically gastown, if we're calling that a harness).
Pi is... just fine.
It does what I need it to, has a decent selection of tooling out of the box, integrates nicely with other tools, and generally gets out of my way enough that I don't think about it much anymore.
If you can run ~30b models at decent speeds, I think most folks would be pleasantly surprised at how capable they are with pi.
Which is something that all the other providers charge you api access rates for (ex - thousands a month).
Insanity 3 hours ago [-]
Heard good things about pi.dev but haven’t tried it. It might take care of some of those missing features you mentioned.
bityard 3 hours ago [-]
pi.dev is more like an agent developer kit. It's basically a substrate upon which you spend hours/days/weeks building your own agents or coding framework. It's pretty much the neovim to claude's vscode.
horsawlarway 2 hours ago [-]
I mean - the base experience is just fine, with perfectly reasonable built in tools for file access and editing, plus bash.
But yes - it expands a lot if you're willing to play with it.
I'd actually say the vscode comparison is wrong, because vscode is very much "bring your own extension" in the same way that Pi is. While Claude is much more "visual studio" vibes. It's thick, it's opinionated, and it's absolutely not something you can really customize, but it can feel slick for supported workflows.
cheekygeeky 3 hours ago [-]
Our software dev (smartest guy I ever met) is using OpenCode and Tmux with Open Source models. He says the DeepSeek is his model of choice for coding (he call's it "pretty GOOD". He's running two 3090s on an i9 with 128GB RAM. https://www.msn.com/en-us/news/technology/china-s-open-deeps...
thrownaway561 7 minutes ago [-]
I just use DeepSeekV4 Fast... It's cheap as hell. Currently my monthly usage has been
67M Ouput
51M Input
Total $0.83 dollar.
I honestly don't understand why people just don't use DeepSeek.
anuramat 43 minutes ago [-]
I wonder what languages people are using; I imagine smaller models would be decent at bash/python but significantly worse at something like rust
bArray 1 hours ago [-]
I'm in the middle of building my own based on LiquidAI/LFM2.5-1.2B-Instruct [1]. I run it on the CPU locally and get reasonable performance. I'm currently using it to solve small problems - but expanding it daily.
I wish someone would do a benchmark and competition for this kind of work flow so we could figure out what works well.
Like "Here's this consumer grade GPU. Using only this GPU but with whatever models and workflow you want, see how well you can do on xyz benchmark."
Contestants would be given like 1 hour max and scored based on % of questions answered, % of questions correct and total time to finish.
Like "The Local AI challenge"
whartung 1 hours ago [-]
Will the inevitable M5 releases from Apple change this equation in any meaningful way?
I'm waiting to swap out my last gen Intel iMac with a new M5 mini of some kind, with the eye to hopefully be able to run some models locally. I envision a mini (heh) arms race to simply swapping out an M(X-1) for an M(X) annually as this field shakes out.
zaptheimpaler 2 hours ago [-]
I tried gemma-4-26B-A4B just to see if it could help me read/sort my emails on a relatively under-powered setup (16GB VRAM + 32GB RAM) and it's not going well.. the model burns 24K tokens just on searching for the right tool and then dumps the email contents into context - i tried to get it to use code-mode to save context but the code-mode implementation can't save files so it was useless and im going to try to switch to "ssh-mode" into my devbox container. Still relatively new to this, so I'm probably doing something wrong
anana_ 2 hours ago [-]
Perhaps try a different model? Just from anecdotal experience, I find that the Gemma models smaller than 31B do not tool call as often as they should.
Some of the benchmarks appear to back this up [0]
Of course, a lot depends how you are using it (inference parameters, harness, prompting, etc.), but the model is quite important too.
Tried. The context windows just weren't big enough.
coder543 1 hours ago [-]
Qwen3.6-27B supports a 1 million token context window.
Of course, you have to have the right hardware to be able to run with a context window like that, as it takes about 100GB of memory on my DGX Spark to do that with full f16 KV cache on the q4_k_xl model.
deadbabe 3 hours ago [-]
Prompt more directly instead of open ended.
lysace 3 hours ago [-]
Got a similar result (my RTX 4070 only has 12 GB). I'm curious about whether 24/32 GB meaningfully improves this enough to make it useful.
Local isn't new for me. I am still coding my stuff, but Qwen3-coder:30b on my old rig with a gtx 1070 16gb RAM does wonders for me.
I mostly use it as a google search if I forget a thing, or doing the boilerplates.
I am using a mix of a non harness chat for the reply speed, and opencode / vim-ai for my boilerplates.
$0.00 / month. That's the budget.
mark_l_watson 1 hours ago [-]
I would like to say I run 100% local, but I use Opus + Gemini Pro cumulatively for 3 or 4 hours a week. I also like to use DeepSeek v4 flash with OpenCode for small quick tasks.
I did just publish a free to read online book "The Rise of Local Coding Agents" [1] where I document my setup that I enjoy using. I use little-coder (built on pi) and have good results for small Python and TypeScript applications. I struggle getting good results with Common Lisp and Clojure.
For me, the problem with all local LLM-basic coding agents is slow runtime.
Is anyone managing to do this on a Mac with a measly 8GB ? Asking for a friend.
xhinker2 2 hours ago [-]
Yes, I have.
1. Two RTX 3090s in Linux 22.04
2. Running Qwen3.6-27B Q6_K_XL GGUF
3. Using my own harness AZPal, I build myself, also wire it with Hermes Agent, works fine
4. Many times it solve problem that Codex can't solve
I tried for a bit, with llama.cpp + Qwen + Mac Pro but the results were very poor (both quality and speed).
I considered investing in better hardware but doing the math, it is cheaper for me to pay for DeepSeek (yeah, I know not everyone can do that).
NetOpWibby 3 hours ago [-]
I'm looking forward to having Claude Fable at home. THAT is when I'll THINK about replacing Claude (who knows what their next models will be capable of, Fable was damn good for the three days I had it).
trueno 2 hours ago [-]
we keep moving the goalposts on when we're gonna be happy with local. first it was sonnet at home as the good enough, then opus, now it's the mysterious leading model that runs on infrastructure we can't feasibly have at home
boringg 3 hours ago [-]
Will the AI labs always make sure there is at least a years worth of differential? I guess the underlying business premise is that each new release has a step function change that prevents this kind of behaviour..
shironnnn_ 1 hours ago [-]
I use SpecKit to create a very detailed plan with a high amount of specificity using paid Claude plan.
Then I give it to local LLM (eg: Qwen / Gemma 4) via CLI. This is possible through usage of llm-mlx on Mac (or ollama on any machine given sufficient on hardware) which serve OpenAPI endpoints compatible for Aider (CLI) or Visual Studio Code to vibe along with the agentic coding assistant.
The paid products have an advantage but are not necessary if you don't mind to be more-involved with the process and have low expectations.
mv4 2 hours ago [-]
I've been using MiniMax M2.7 with vllm on my dual Nvidia Spark cluster. Slow (<20 tps) but functional for most of my use cases.
dabinat 3 hours ago [-]
There’s evidence that combining models can achieve frontier-level performance (e.g. OpenRouter Fusion). I’m wondering if that’s the more realistic option: combine Opus with a local model to save on token costs.
rvnx 1 hours ago [-]
I start to believe that adding more and more and more and more and more thinking tokens is the hack that works (this is what gave birth to Fable)
sometimelurker 18 minutes ago [-]
yeah I use one one the small MTP qwens and pi
jmward01 2 hours ago [-]
Has anyone been storing their cc sessions for future training data on their own models? I'd love to build a system that fine-tunes on cc sessions and a good first step is capturing my own sessions well.
Didn't realize they did this. I have avoided pushing data to huggingface. This is all -deeply- private info and I haven't really reviewed their privacy policies and the like. I'll give them a look.
tyingq 1 hours ago [-]
Anyone doing it with a "rent a GPU over the network" path? Is that at all cost effective for any use case?
Not yet, tried Gemma 4 on an Apple M4 but the tok/s is significant lower than the cloud offering.
Also,the lack of enterprise tooling to help selected an appropriate model and tooling to run a local LLM does not help.
Lwerewolf 3 hours ago [-]
mbp16 m5 max 128gb, antirez/ds4, deepseekv4-flash. Works well for relatively dense (let's say <20k LoC per project) C codebases that are essentially a bunch of custom specialized stores, http servers, network infra, media transformers, etc.
Runs through Pi with a custom prompt (basically "don't speculate blindly, isolate things, make them traceable and measurable, then verify") and behind a pretty restrictive bwrap setup - RO bind everything other than ~/.pi, cdw and a separate tmpfs, unshare almost everything other than the network - for which I use a network namespace that only allows tcp connections to a specific ip and port (i.e the inference mac) - i.e. netns exec into bwrap.
Can't compare it to SOTA or higher-requirements models on what I work on - policy. That said, on a bunch of test pieces - it obviously isn't gpt-5.5, it definitely lags behind k2.6/glm/ds4-pro, but it absolutely is usable. Of course, on such codebases, forget about one-shotting or trusting it blindly or anything of the sort - you ask it, guide it, restart the context from time to time to have a "fresh dice roll" and to keep the context small and clean, etc. Compared to anything smaller (incl. all the usual local qwen models) - on a test piece, it figured out that memfd and mmap were used for setting up a ring buffer with natural wraparound handling (double mapping the first page at the end) and didn't tell me "this is for sharing memory between processes" or some other BS.
Performance as described in the tables in the readme here:
https://github.com/antirez/ds4
...with a bit less than half that at "low power" (30w). Both are usable.
drnick1 47 minutes ago [-]
Do you recommend Ollama or bare llama.cpp?
wuschel 3 hours ago [-]
I would like to know whether someone was able to use lower tier models for activities other than coding e.g. a limited version of a personal note manager - and what the hardware requirements in RAM for these models were.
hegdeezy 3 hours ago [-]
I have tried locally but I find that the implicit breakeven is somewhere around 1 year of use given the high power costs where I live. Not really worth it but maybe if I move some day!
fortyseven 3 hours ago [-]
I use Pi and Qwen 3.6 27b locally on a 4090 for all my personal projects. I still use Claude for day job work since they pay for it, and my employer expects me to use it. I rarely touch it otherwise.
AH4oFVbPT4f8 2 hours ago [-]
Ollama + Hermes on M5 Max 128GB using .NET using Qwen 3.6:35b-a3b as the primary model to do the work. I might use 27b to plan what to do.
xeonax 2 hours ago [-]
Whats .NET doing in between?
AH4oFVbPT4f8 9 minutes ago [-]
Sorry, I meant to say I was writing .NET C# with the setup
ryandrake 4 hours ago [-]
Always a bit disappointed in the details in these kinds of threads. When you do get answers, they're never specific enough to try out on your own. It'll be something like "I use Qwen 3.5 and get great results!" OK but what quantization are you using? What llama parameters? What context size? What GPU are you running it on, and how much VRAM does it have? Are you hosting it on a separate box, or running it locally on your dev machine? What coding agent tool are you using, and how is it configured / hooked up to the model?
riazrizvi 3 hours ago [-]
All you get here is some market signal from 1 or 2 posts if you already know how to do it. Most of these responses are garbage.
porkloin 2 hours ago [-]
I have good results with this setup:
Hardware:
- GPU: AMD 7900xtx, 24gb vram
- CPU: AMD 5950x, AM4
- RAM: 64gb DDR4 3600
Software:
- OS: Bazzite (atomic fedora - this machine is running Steam "big picture" mode on my TV when not in use for LLM tasks)
- Virtualization: Podman Quadlets, which allows me to run container images as managed systemd units
- Network: tailscale
- Inference: llama.cpp vulkan (better performance than ROCM, though I'm keeping an eye on it in the future)
- LLM API surface: llama-swap (running as a podman quadlet exposed via tailscale svc) allows running multiple models on a single endpoint.
- Web/Chat Access: open-webui (running as podman quadlet exposed via tailscale svc) allows me to access any of the models I'm using for coding harness access for chat/general purpose queries via web browser. I also have the "conduit" app for my iPhone that allows me to hit the same models from my phone.
Models:
- Qwen3.6-27B-MTP-UD-Q4_K_XL.gguf - Unsloth Q4 quant of the qwen 3.6 27B model weights, with MTP enabled. MTP is important as it improves the speed the model can run at.
- Qwen3.6-35B-A3B-UD-Q4_K_XL.gguf - Unsloth Q4 quant of 35B-A3B. Not MTP right now because I was having some issues with it?
- gemma-4-26B-A4B-it-UD-Q4_K_XL.gguf - Gemma 4, which I use sometimes via open-webui instead of Qwen, but I generally think Qwen does a better job
Flags (specific for Qwen 27b, since that's primary model):
- `-ngl 99` offload all layers to GPU
- `-c 80000` 80K context window. I'd like this to be higher, but since my GPU also has to run the desktop session for the machine, I need to leave some VRAM overhead to keep the desktop from OOM-ing
- `-np 1` single slot (no parallel request handling)
- `--no-context-shift` error instead of silently sliding the context window when full
- `--cache-reuse 256` reuse cached prefix in chunks of 256 tokens (prompt cache)
- `-b 2048` logical batch size (tokens per submission)
- `-ub 1024` physical micro-batch (per GPU pass)
- `--cache-type-k q8_0 --cache-type-v q8_0` symmetric 8-bit K/V cache. Q8 is as low as I've been able to go without getting some issues with tool calling
- `-fa on` flash attention
- `--spec-type draft-mtp` use the model's built-in MTP as the draft model
- `--spec-draft-n-max 3` propose up to 3 draft tokens per step
- `--spec-draft-n-min 0` allow zero drafts if confidence is low
- `--spec-draft-type-k q8_0 --spec-draft-type-v q8_0` KV quant for the draft path
- `--reasoning-format deepseek` parse <think> blocks in proper format
- `--chat-template-kwargs '{"enable_thinking": true}'` turns on Qwen's thinking mode on by default (clients can override)
- `--jinja` use the GGUF's Jinja chat template
- `--temp 0.6` moderate randomness (Qwen recommended value for coding)
- `--top-p 0.95` nucleus sampling (Qwen recommended value for coding)
- `--top-k 20` top-20 candidates (Qwen recommended value for coding)
- `--min-p 0.0 disabled (Qwen recommended value for coding)
Performance (27b, primary model):
- ~65t/s for token generation
- ~600 t/s for prompt processing.
- If these numbers don't mean much to you, perceptually this feels about on-par with cloud model speed, maybe slightly faster.
- ~30s cold start when swapping from a different model or starting up session from idle via llama-swap.
I have llama-swap set up to unload the model after 10 min of idle, because I sometimes use this machine for gaming as well. A little annoying, but a small price to pay to be able to use the machine for other stuff (gaming) when I'm not using it with coding tasks.
CLI/Harness:
- Crush harness (https://github.com/charmbracelet/crush) less feature rich than Claude Code, but with a smaller system prompt and better built-in LSP support. I point it at the tailnet DNS (https://llama.<tailnet>:<port>)
- Exa MCP for web search (https://exa.ai/) this alone makes the model far more useable. It's shocking how often the official claude code or codex harness get botblocked on web fetches, and the results of a good web fetch can be the difference between a good turn and a bad turn.
A lot of people get hung up on whether Qwen 3.x models are "as smart as" some parallel Anthropic model. Most people seem to agree it's somewhere between Haiku 4.5 and Sonnet 4.5. Personally, I think the biggest thing that makes the Qwen 3.x series of models _feel_ good to use for coding workflows is that its the first time that tool calling actually works consistently on local models. If tool calling is busted even 5% of the time, it can totally ruin the flow. I think that's also why people tend to say the "harness is more important than the model" or whatever. I have a few other models set up but 27B with MTP is the best compromise of speed and quality that I've found.
This setup works well enough for me that I dropped my personal Claude Code subscription. At work I'm still using frontier models, but personally I don't feel like I need that much power for anything I work on in my personal life. I'm "lucky" that I made the random financially unwise choice to buy a 7900XTX in late 2022 for $1k as a gaming card. I had no clue it would actually be a pretty decent LLM card 3-4 years later.
Edit: sorry for the horrible formatting, I always forget that HN doesn't actually do markdown :(
ryandrake 2 hours ago [-]
Now that's what I'm talking about! Very cool, thank you for the detailed response.
ecshafer 4 hours ago [-]
I work with a few models on servers, so not local, but self hosted with ollama. gemma-4, glm 4.7 flash, and qwen 3.6. glm is the best at coding agentically. But I still don't think any of them reach the levels of gpt 5.5 or opus 4.8.
wmedrano 1 hours ago [-]
No, but I use GLM5.1 instead of Claude/GPT.
_davide_ 4 hours ago [-]
i used to mix remote and local minimax 2.7(q3) on my strix halo, it run at 30 tg and 220 tokens pp... it was a bit painful slow, but it was a good feeling i could stay offline. unfortunately m3 which is at opus .8 levels is 460b parameters and doesn't even fit in 128gb of memory, let alone a big context. strix halo feels like a toy for ai purposes. https://kyuz0.github.io/amd-strix-halo-toolboxes/
sosodev 3 hours ago [-]
My strix halo board is feeling more useful and less toylike with the recent performance gains combined from MTP, better quantization, and generalized performance improvements across the stack. For example, I can run Unsloth's Gemma4-31B 4-bit QAT model with around 30tg and 200pp. I don't find that to be too slow at all. Particularly because it's nearly full accuracy and good enough for a lot of different stuff I throw at it.
I think it also helps that I'm using my machine to do home server stuff. It excels at all of the traditional workloads. Then I can lean on the AI to help with automation here and there. I find it deeply satisfying.
_davide_ 1 hours ago [-]
you can absolutely use it for some workloads, but as soon as you have some extra complexity for a big repo it'll take forever and the economics are so silly to the point that the electricity bill would be comparable to a subscription. I love having the possibility of running things locally if some random dude decide to pull them plug, and give me solice the fact that i can have 100% private inference, but as the main driver during the day? shoot me
SkitterKherpi 3 hours ago [-]
It has so far been the kind of thing that always feels like the next version of the local models would be the one that is just good enough.
jwr 3 hours ago [-]
I tried many, many times and I keep trying. But I just don't see this happening: those tiny models that we can run on our machines (I have an M4 Max Mac, so I can reasonably run qwen3.6-35b-a3b or gemma-4-26b-a4b-qat at this time) are NOWHERE near as smart as the huge monsters like Opus/Fable. Nowhere. I can see a lot of people deluding themselves.
Sure, you can get the local models to generate plausibly-looking code for simple cases. But compared to how I solve complex design problems in a large codebase with Claude Code and Opus/Fable, this isn't worth my time.
jmichaelson 3 hours ago [-]
I am working on exactly this issue right now. My approach is that a highly optimized harness (pi.dev) with the right backing knowledgebase (a custom, self-updating wiki with lots of QC layers) can get close to most of my usage patterns for my Claude Max 20x subscription. I use Gemma 4 26B QAT served by a custom fork of llama.cpp, with 4-8 slots of 256k context at Q8. It's a very good model when the harness keeps it on rails. In an age of 1M context windows, 256k may seem small but it's been plenty for my work (scientific programming). A $20/month subscription to Ollama-cloud gets me good coverage of consults out to frontier models for difficult plans or debugging (again this is all woven into my highly customized pi install).
I'm still optimizing it (with claude, to be clear), but my testing is very encouraging. I worry a lot about companies (and the government) controlling access to machine intelligence, so local is the way to go.
dada216 3 hours ago [-]
Local? No.
Via opencode Go subscription using GLM mainly? Yes, I still use Gemini/Claude/GPT via api from openrouter for adjacent tasks, I would say 20$ per month max in api token costs.
Disclaimer: I am a Linux infra/k8s guy, I write production code but it's mainly glue code and mainly in golang.
Addendum: most value we get is from "document intelligence" and that's all Gemma and Qwen on H100/H200
w10-1 1 hours ago [-]
I run many models (but mainly Gemma-4) using oMLX (for caching) on a 32GB M1 max using (gasp) Xcode. For tok/sec response times, I'd say it responds faster than I could read the prompt aloud in many cases (and I'm not constantly polling the Claude status page).
For months I spent time curating the AI+harness+skills+MCP servers, but now mainly just code with it. I find myself not bothering to use Claude (but keep paying "just in case").
That's feasible in part because my prompts have very specific objectives, constraints, and suggested staging, because I want the code to be exactly as I would write it, and I want to weigh in at specific moments. I would say the speed-up is 2-4X instead of the 10X of vibe-coding greenfield projects. The problem is not the coding speed, but building something complicated that's also correct and flexible (i.e., a directional accuracy). E.g., the agents help with abandoning a less-fruitful API shape instead of sticking with what works in a local maxima.
One flaw there is that I'm still writing code that feels clean to humans, which now is probably a waste. LLM's might be happier with 10+ parameters on one API instead of a plethora of configuration objects and convenience wrappers.
Related: Are there any viable distributed AI models?
Like how we've had SETI at Home, Folding at Home, BitTorrent etc. People are clearly willing to donate their computer resources to distributed projects.
Maybe in a dAI network anyone could submit content for training on, and each user running a "node" could have their own custom private conditions on which type of content to accept for training or inference.
Like someone who dislikes anime could say "never accept anime related content or queries" so their node would basically opt-out from any data or questions about anime.
3 hours ago [-]
joshuamoyers 4 hours ago [-]
I think it'd be very hard to achieve viable tokens/s or get arithmetic intensity to be high enough in general, since many cases in existing training and inference are memory bandwidth limited. Definitely seems possible to conceptually have a slow pipeline that is distributed though.
SimianSci 2 hours ago [-]
This is unlikely to happen in any meaningful fashion for quite some time.
(TLDR; Distributed compute for models will require hardware at a level only really possible with data-centers at the moment.)
Token generation operates at such a scale to demand enough from a single GPU as it will often saturate the bandwidth capabilities of consumer grade interconnects like PCIe. Which fundamentally implies that distributing a model's compute across vast distances is too much of a challenge without significant infrastructure.
To give an example, When we split a model's compute between two seperate cards on a single workstation, this doesnt mean we end up with 2x the compute bandwidth for a model. Instead the increase becomes something small like 20% depending on model, because the inconnects (PCIe on consumer hardware) will quickly become so saturated with data being copied between the two GPUs so as to become a bottleneck. And remember that this is something that happens locally with PCIe, which (depending on generation) will cap out at around 20-35 GB/s depending on the generation of motherboard.
Model performance is very much tied to having the fastest and highest bandwidth single card available so as to keep data transfer operations to a minimum as the sheer volume of data necessary for the model to run is immense.
I simply cant imagine how slow and unusable a model would be if the copy operations necessary for its compute needed to be performed over unreliable network speeds where there will be significant performance loss as network speeds are not reliably distributed across the globe, and their unreliable nature would demand increased overhead due to data verification.
The dream of distributed AI is a ways off.
jeffrallen 1 hours ago [-]
I use Qwen 3.6 on a remote GPU that my work offers. Works fine. Slow and steady, works hard, gets the job done. Probably better at diagnosing than making new code, but whatever.
major505 2 hours ago [-]
Yes. I use Owen on my MacBook m1 (16gb) daily, running inside Ollama. Works well. Is not particularly fast, and I need to create a custom imagem that sets the temperature of the model to zero starting, so I don't get over creative with its bullshit, but it works reasonable week.
system2 3 hours ago [-]
Until I can buy an 80GB VRAM GPU, I won't attempt to do it. A local LLM is always missing something that needs a bigger model.
I tried to. I just couldn't get over how it made my otherwise whisper quiet M3 Max MacBook Pro 14 for the performance. The sweet spot has been adopting Claude Code to use the Chinese models. Deepseek V4 Pro is very, very good. But I am such a casual local user of AI that my 20/month Claude subscription is enough and I find myself using that more and more.
cyanydeez 2 hours ago [-]
never started. using wither qwne3-xoder-nezt or qwen3.6 35b
if youre shoopping for a new pc, very easy to justify 128gb vram
dude250711 4 hours ago [-]
Yes, running a local model on a natural wetware substrate here.
Recommended setup: plenty of nutrients, some caffeine and a quiet environment.
Performance - not currently measured in tokens: roughly average.
jasongill 3 hours ago [-]
I have been running this stack since well before Claude Code became popular. It works OK but I've found it to be very slow; and despite having a big context window, it seems to lose track of what it's working on and goes down a rabbit hole (or just wastes tokens trying to use the web browser) for hours and is hard to get back on track. I even tried spinning up two sub-agents but even after years of trying to prompt them, they are almost useless in terms of coding ability, so that is looking to be a waste of spending at least so far but maybe the model will improve as time goes on.
HPsquared 4 hours ago [-]
I personally get about 50 tokens per hour.
KaiShips 1 hours ago [-]
[flagged]
ericmaciver 17 minutes ago [-]
[dead]
eugmai86 2 hours ago [-]
[flagged]
temilson 3 hours ago [-]
[flagged]
phlhar 4 hours ago [-]
[dead]
iluvcommunism 4 hours ago [-]
[dead]
kertoip_1 4 hours ago [-]
Just attach OpenRouter to your coding agent tool and try yourself. All relevant open weight models are there. Every person have different needs and expectations
I've noticed a few things compared to large models like Claude. For starters, you really need to know what you're asking, and be precise; it doesn't do much thinking for you. Any assumptions left open, and it'll take the easiest route to reach the goal (e.g. CSS in HTML), often not the best in terms of architecture.
It gets into loops quite often, and surprisingly often gets the edit tool call wrong, after which it will spend lots of thinking tokens and re-read files instead of retrying (despite the system prompt suggesting so).
Comparing agentic Qwen3.6 35b to Claude Opus is like a junior with knowledge across the board, that you really need to guide, versus a senior that thinks with you on architecture. If Opus gives a 15x speedup, local and fully offline Qwen gives a 5x speedup. Which, given that it's completely free, is still mind-boggling to me :)
I've never used the frontier models in earnest, I don't believe in using proprietary tools for my programming, so I can't really compare.
And I'm still a AI skeptic, so I'm doing more testing and kicking the tires than I am actually using it. That means I spend a lot of time trying to break various models, probe them for strengths and weaknesses, etc.
But I find that when I do try to use it for real for agentic coding, Qwen 3.6 35B-A3B is definitely the one I reach for the most often.
For other chat tasks and translation, I'll frequently use Gemma 4 31B.
For audio, I'll use Gemma 4 12B.
I keep a bunch of other models around to try out every once in a while (Qwen 3.5 122B-A10B, Qwen 3.6 27B, Nemotron 3 Super 122B-A12B, Step 3.7 Flash and Minimax M2.7 both at somewhat more aggressive quants, and GPT-OSS 120B if I want super fast but not terribly smart), but so far Qwen 3.6 35B-A3B is really the sweet spot for coding on a setup like this.
The re-processing context every turn problem is definitely something I've hit. Some of the causes have been solved upstream in llama.cpp; make sure you're up to date.
But another cause of the issue that has a big effect is that older Qwen models didn't support preserving thinking. This means that each time you have a long sequence of tool calls with interleaved thinkging, as soon as you had your next turn in the chat, it would have to re-process all of that as it would drop all of the reasoning.
Qwen 3.6, however, now supports preserving thinking. This can use a bit more context, becasue you're not dropping the thinking every turn, but it re-uses the cache better, not causing you to have to reprocess a whole turn at a time each time.
In my models.ini, I have this for the Qwen3.6 models:
There are still occasional issues I hit where it will have to re-process, but getting up to date and enabling preserve_thinking has helped a ton.I'll have to give the preserve_thinking a shot.
I've had the best luck with Pi so far, but it comes without some bells and whistles you might be used to (e.g. plan mode, subagents, MCP client support)
I didn't do much benchmarking, but anecdotally, I found it to be making less edit errors. YMMV
I do (unscientifically) experiment whenever a new capable local LLM (<=130b) releases with a license that permits commercial use. As for knowing my models require more work than Opus, I don't mind still having to puzzle on getting the architecture right. In any case, it forces me to stay in the loop of what's being built, which is a good thing.
I find that running better quantization, like Q8 tend to prevent this even though its a bit slower to run, it saves overall time with less churn
Using 3.6-27b is even slower again than 3.6-35b, but I find the accuracy really pays off
Now, there's a bit of a degree to which some of the open source models do some benchmaxxing, and bigger models with more params may always feel like they have more depth. But anyhow, right now you have something that is arguably comparable to Claude 4 Opus on your laptop. I can't really compare myself because I never used it. It looks like Claude 4 Opus is still available on OpenRouter, so you could try it out and compare yourself if you're interested.
It will likely always be the case that there are proprietary cloud models that are more powerful than what you can run on a laptop. You can just do a whole lot more with terabytes of VRAM on multi-GPU clusters than you can do on a laptop. So for folks who must have the most capable, you're probably not going to want to leave Anthropic.
But right now, the models you can run on your laptop are comparable to the cloud models that were popular when vibecoding and Claude Code first took off.
Anyhow, feel free to try them out head to head on OpenRouter. I'd love to see someone write up their results, of a modern local sized open source model vs. frontier models from ~a year ago, on something other than the standard benchmarks.
Two years later, and I'm running Qwen3.6 35b agentically to develop the start of a repository and automatically run tests to then improve on itself. I never thought we'd get here so quickly with LLMs back then.
I'm pretty sure in two years we'll have current Opus-like quality in the 30-100b parameter model range. But at that point, Opus 6.3 will reason along for us so much better still, that we'll still look at those models in awe. It's great to look ahead, but let's not forget to appreciate how effective the current local models already are :)
It's personal, but I prefer CapEx over OpEx for this. If you can purchase a device upfront that runs a decent local LLM, you get the peace of mind that your setup won't suddenly change over time and can only get better.
OpenAI was offering 2x usage at one point and I still used opus just because it's so much more effective.
More and more specialized and ultra-performant chips are going to flood the consumer market. Especially once new hardware foundries will start producing (well if we don't die from WW3 in the interval).
In 10 years from now, when even basic computers will have 128 GB of memory, and phones will have super optimized tuned models, then what will be the point of Anthropic ?
Just use Gemma/Gemini/Siri or whatever.
Pornography and uncensored models is also pushing toward local models.
It's not like needs of people grows exponentially, the needs follow an asymptote instead (they are capped).
The real revolution is offline robots and self-driving cars, but LLMs are already quite maxed.
For programmers, now, what Anthropic offers is like 3% improvement on a known test (like this pelican riding a bicycle), or on questions leaked from benchmark insiders.
It's ok but not like revolutionary (Fable was better but it was unusable, easy 20 minutes per one prompt due to overthinking).
And then also, sometimes the tool call errors are because of something like a file was changed out from under it; the larger model is probably going to do a better job of figuring that out and fixing it up.
Finally, in Pi, you can always just use the /tree command to skip back to before a series of failed tool calls, with a summary if you want to let the model know what happened. The Pi /tree command is pretty powerful in managing your context
I'll experiment more with the effectiveness of AGENTS.md rules for local Pi agents. I feel like smaller (local) LLMs just lack in attentiveness to elements in the context window, like precise instructions, compared to e.g. Claude models.
matches my experience and a deal breaker
also the context window sizes are too low. I can't operate in 65,000 windows any more because even just reading the code's file structure overruns it and gets me nowhere. Definitely its own art form.
200k context windows and above for me now
I saw a paper last night that should help this a lot though
In Pi, /new is my best friend and most-used command for sure. For simple tasks (I decompose complex ones anyway since I don't trust small local LLMs to do this for me), the model doesn't need much context, given that I'm proficient in my codebase myself: "I'd like Feature X. Look into files 1, 2 and 3 to make your edits."
I replaced a $100/m subscription to claude in favor of running pi harness pointed at unsloth studio, using both qwen (unsloth/Qwen3.6-35B-A3B-MTP-GGUF) and gemma (unsloth/gemma-4-26B-A4B-it-GGUF) models, depending on my mood.
I have a machine I built about 5 years ago with dual RTX3090s in it (I was going to build a new gaming machine anyways, and the llama release had just dropped so I tacked another used 3090 onto the build), and I get ~150tok/s on either of those models (at UD-Q4_K_XL quant) and can use the entire 300k context length without having to exit VRAM.
To be very clear - it's not as good as claude. But it's free and not so much worse that it matters significantly.
For my personal needs, free beats $100/m.
I also have an openclaw instance pointed at the same inference server, and it's great for that (genuinely solid use-case for local models).
Some example projects
- Replacement launcher for android tvs (with usage monitoring and tracking for kids)
- Custom admin portals for my k8s cluster services
- Custom home assistant integrations/automations (recently some shelly devices for power monitoring and switching)
- Grocery list management and meal planning (mostly via openclaw)
- some custom workflows for 3d asset generation in comfyui.
---
Long story short, if you're trying to make money via software... I'd probably still recommend using a paid provider. But the local models are very capable of cool stuff.
Also, 2 gens old means bad performance at ray tracing, abysmal path tracing if at all. Pretty sure it can't run smoothly CP2077 in native 4k without dlss upscalers with all on ultra.
When I bought, I paid $850 a piece. And I needed one anyways for the gaming I was going to do.
My guess is the next good time to buy is going to be 24-36 months from now, depending on how the AI bubble goes.
---
I'll add to this, I personally don't like Apple hardware (not so much related to the hardware as their company philosophy) but their machines with unified memory (or AMDs latest unified memory offerings) get pretty equivalent speeds to my 3090s, and are probably a much better modern entrypoint to local llms.
There's a reason the joke is that Silicon Valley software devs bought up all the Mac minis for OpenClaw.
You can get a 48gb unified RAM M4 pro mac mini for ~2k. If you're not going to do much else with the machine, it's what I'd pick as my budget inference device right now. Spend a year of claude now, get ~150tok/s for the next decade (plus) for ~free.
If you want more capable and are willing to spend a little more, go with the newer Ryzen AI Max+ 395 machines.
You'll spend less on power too.
My last suggestion would be to go buy an RTX3090 at this point. You can do a lot better for a lot cheaper.
How do AMD cards perform with LLMs? A 9070 is sold for ~$600 and has 16GB VRAM
16 GiB won't fit you much, so you'd probably want at least 2x, and preferably 3x of those, and then you need a motherboard, power, etc. that can handle that.
Since you're running quantized (at UD-Q4_K_XL) , check out the "qat" models (unsloth/gemma-4-26B-A4B-it-qat-GGUF) !
- https://huggingface.co/unsloth/gemma-4-26B-A4B-it-qat-GGUF (With "Jun 9 Update: Added MTP support.")
- https://blog.google/innovation-and-ai/technology/developers-...
> Quantization-Aware Training (QAT) [...] allows preserving similar quality to bfloat16 while dramatically reducing the memory requirements to load the model
I've actually tried this exact same model locally as well.. albeit on just a single 3090 at 128k context and I got around 40-60tok/s with Q4_K quantization.
The thing that bugged me the most was really the quality of the output on moderately complex real-world coding tasks. Having to switch between "prompt/vibe" and "manually implement" is such a big context switch burden, because you really have to ask yourself every few minutes if you're "holding it wrong" or the model is just too stupid.
It also doesn't really seem to handle transitions from "low-level implementation detail" to "high-level design" well, e.g., it wouldn't easily render tables and such. With Claude I don't have this issue.. so I think for now my verdict would be that it's not really a viable replacement. I really hope it will be in a few months time.
Oh and I used "aider" to replace claude CLI, which maybe that's also sub-optimal.. I'm not sure. The MCP marketplaces are useful of course, though arguably you could just manually replace them over time.
It's prone to thinking longer and more repetitively, again - it's definitely not opus 4.7/4.8.
I've been using pi.dev as my harness for it, and been pleasantly surprised by how nice it feels (I have used aider, but only very briefly and quite a while back - so I can't realistically compare).
I would say it's roughly where I felt claude was a year back - Most of the sessions need to be more "pair programming" and less "I let it run for hours".
I'm a big fan of frequent "human in the loop" style workflows even when I'm on something like opus at work, though. I have opinions about lots of things, and re-inforcing that the model should stop and ask frequently seems to get me considerably better output, without having to "re-roll" if you will.
I've done a good bit of management, and I think it's roughly producing what a junior dev might produce in a day every 5 minutes. And just like a junior dev, you need to be steering it back on track fairly often.
Opus feels more like a mid-level at this point. I can hand it a chunk of work and "leave" but I still get better output if I'm checked-in and watching/steering.
I've used Claude Opus to quickly and effectively pound out some 100-200 line scripts that integrate with a vendor's API, and it one-shotted them both almost perfectly.
I wonder if for a lot of these local models, the scope of the AI assistance should simply be smaller: You architect the tools and the function definitions, and then tell AI to implement one at a time? Does anyone do that rigorously?
A single RTX-3090 will do approximately the same tok/s, but it won't fit the entire 300k context in VRAM.
Sometimes that matters, a lot of times it doesn't.
On the speed front - MOE models are great. Biggest perf difference in modern models is the move to MOE architectures.
I get very similar quality from the both the Gemma-4 31B dense model, and the Gemma-4 26B MOE model (both at Q4 quant) but the MOE version runs at ~3 times the speed (150tok/s vs 46tok/s).
Other Notes: I have had to set the compact target to 75% on a 256k context window as once the conversation length goes about 100k I start seeing a drop in the quality and speed. This becomes very problematic after about 150k. I tried Qwen 3.5 122b too but it actually seems much worse at coding than 3.6 27b even though its much larger. Maybe because I am using a 4bit quant or maybe I just don't have it configured correctly? I know 3.6 is newer but I didn't expect it to out perform a model that is much larger from the prior generation. Gemma 4 31b is a good model for other tasks but at least my personal experience is that Qwen outperforms in coding. Nemotron Super 120b is great at a lot of stuff but it also seems to be not as good at coding as Qwen. This was very surprising to me.
I have become so "lazy" (in a good way), so far that I've started using the model for lots of daily mundane things on top of just coding:
That sounds great for hobbyists but IMHO it wasn't until Opus 4.6 was released six months go (Dec 25, 2025) that we had a model good enough for professionals to use as a primary driver of their coding agents. That seems to be the threshold worth aiming for.
in my stuff now i use an OT library that claude put finishing touches on in September.
Regardless I don't think it's fruitful to be so condescending with such little insight into this person's situation. Even if you had total insight -- let people be and withhold your judgement, or at least keep it to yourself. Making people feel stupid is a great way to turn people off to pretty much anything else you have to say
i always see great debates with local stuff but the space is constantly moving goalposts and all the vernacular is pretty unfamiliar to me. i'd love to understand what people with objective experience feel they've traded away (or gained) when going local so i can determine for myself if these things are a good fit.
> "Quality is like running edge models from 8-12 months ago"
Don't expect Opus, expect more like Haiku. If you micromanage it, you'll get great results. If you want it to be a human in a box, it'll flounder.
I'm looking at https://ollama.com/search and the top few models like kimi-k2.7-code say "cloud" and I can't seem to ollama pull them.
I thought the whole POINT of ollama was not-cloud?
It was at first, then the developers realized they had a massive userbase they could monetize. A tale as old as open source...
Every month I research this and come to the same conclusion: the time, effort, and cost required to get local models (and the coding tools around them) to perform even close to Claude Code with sonnet/opus just not worth it right now. If it was, it would be distributive enough to be in the news.
Not that I'm discounting someone hasn't already solved this, just trying to Occam razor my way out of diving too deep down rabbit holes.
The present Sonnet/Opus versions (~4.8) will likely be what everyone in the enterprise might end up using eventually. And even though local models aren't there yet, there are budget alternatives from the families of DeepSeek, Kimi, GPT, MiniMax, etc. available through APIs of NVidida, OpenRouter, Groq, etc. which are very much Sonnet grade.
Personally, I don't think we're at that point yet. While I do think model improvement is starting to plateau (reaching a local ceiling), I'm not convinced local models are as good as sonnet/opus yet. The gap is still too much. But I'm excited for those models to reach those levels.
With a layered approach we can slowly shift to running more locally and still get required work done. Really, my local setup is so much better than it was 2 months ago, and extremely better than 6 months ago - on the same hardware.
I think it strongly remains to be seen whether e.g. tokens per second (multiplied or whatever by percieved quality of private model) actually means "better or more useful output."
I strongly suspect it does not. (though I also strongly suspect this will be very difficult to measure because the incentive to lie about metrics here will be so strong.)
What I’m saying is that if local models were actually comparable to Claude Code in practice, we wouldn’t be having threads like this. It would be obvious to the people using them, and it would be massively disruptive. Why would individuals and companies pay hundreds or thousands for Claude Code if they could run something locally and consistently get similar results?
Every month I revisit the local ecosystem hoping the answer has changed. So far, my experience has been that it hasn’t.
If you're able to run a model on the scale of ~30B, you can find that with a reasonably scoped and well defined task they do very well. I've found both Gemma4-31B and Qwen3.6-27B to be the best in this range at the moment. You can swap in the MoE models for faster inference, but they are noticeably worse at most tasks. They can one-shot / vibe code tasks with small scope, but still do much better with guidance.
If you really want frontier-like capabilities, you'll probably need at least 128GB of memory and either huge compute or a lot of patience. Most people just don't have either the money or the patience to make these local models work.
The patience required for local model usage goes far beyond just waiting for tokens though. It takes a lot of effort to get things configured and working properly for your workflow and hardware.
I don't think I'd be using AI to code at all if this weren't the case. (I don't want to feel stunted or stuck just from losing my internet connection.)
I am using Opus to generate plans that the local agent then follows, then validated by Opus. So I'm not at 100% local but these models are increasingly part of my production workflow. Probably not worth doing - yet - unless you are a hobbyist who likes spending time and money tinkering.
This setup is certainly not as "good" as Opus or other frontier models but they are "good enough" for an increasing number of rote tasks. You don't need to drive a Rolls Royce to the supermarket, when a used Corolla gets you there just fine.
It also enables new workflows that would be cost-prohibitive with frontier LLMs (especially as token costs rise) - eg. overnight I use the Chrome devtools MCP and have the above setup fuzz-test as a user for a number of hours and see if it can break things. Even got it working with multi-modal so it can check screenshots, which blows my mind (and not my wallet, as Claude+screenshots burns $$$).
The "12-18 months behind frontier" sounds about right, it's about where I was with gpt-4o and basic harnesses back then. In another 12-18 months my bet is we have Opus-level models that can be run locally for <$5k... but the frontier models will be even further forward (unless governments have blocked them). Fun times.
I find it useful.
This side project highlights a similar approach to how I scope and tackle projects at work now:
https://git.theodohertyfamily.com/wg-wrap.git/tree/README.md
https://git.theodohertyfamily.com/wg-wrap.git/tree/CASE_STUD...
You have to apply a lot of careful architecture and TDD to your approach. Eliminate technical risk by tackling hard things early and wrapping them up in a simple, easy to use interface.
I find I can get some projects done 2-3 times faster than if I wrote them by hand. It can also save about 5-10x time on mundane or broadly scoped projects by helping me consolidate and try out ideas very quickly.
Setup-wise, I switch between vLLM using nvidia/Gemma-4-31B-IT-NVFP4 and llama.cpp using unsloth/gemma-4-31B-it-qat-GGUF with MTP. I throttle the GPU power usage to 400W.
My current llama.cpp setup gets token generation rates between 60-150 t/s depending on MTP draft acceptance rates. Prefill is between 1500-4000 t/s depending on context length/depth.
It's kind of like driving a shitbox. It can often drive you from A to B, and some people will try to convince you it's fine. It's not.
There's no logical reason other than absolutely requiring the privacy, doing it for fun, or niche use cases like airplanes and so on. If you can't spend the insanely subsidized $20 for codex, you can use an API for chinese models which will run circles around these tiny models.
Is that characterization based on some objective facts or benchmarks?
Qwen running on my 1st GPU at q4@176k context from 70 to 50 tok/s with MTP, pretty good for coding.
Gemma on the other hand is using both GPUs, running q8@64k context, doing document sentiment analysis, summarization, proofreading and translating, at consistent 25 tok/s. Somewhat slow but usable for batched workflows. Might get some more once llama.cpp starts supporting MTP with tensor split mode.
Still using frontier LLMs at dayjob since I'm not paying it and those are obviously better. Hopefully we'll have a Sonnet 4.6/Opus 4.5 level 30B model in a year or so.
EDIT: Prompt processing starts from 800 t/s and drops to 400 t/s. In most cases my starting prompts are around 16k-24k of tokens and require from 60 to 90 seconds to be processed. Not great but acceptable.
I occasionally use it with pi to write some code and it’s blazing fast but it’s mostly habit that keeps me with CC and Codex.
Where did you find/order these? All the sites I can find are either out of stock, only sell to businesses, or are otherwise sketchy...
The expensive part is the upfront hardware cost and the electrical system upgrade you'll need to give your house.
I've tried other models such as Qwen3.6 35B A3B and I've found that 27B works better for me when it comes to coding. It's slower being a dense model but the quality seems much better. Inference on my system for Qwen3.6 35B A3B is around 130-140 toks/sec, non-MTP, which is insanely fast!
You don't need 4x 5070's to run Qwen3.6 27B, three or maybe even two will work. However, I use MTP (multi-token prediction) to speed up 27B and that eats up more memory because the draft model requires its own context.
Another thing to keep in mind is that the tools you're using have their system prompts that are loaded into the model for each conversation. When I fire up Pi, working with the model is very snappy at start. When I interact with the LLM via Hermes CLI, it's much slower. That's because each prompt with Hermes is loading so much stuff (skills, tools, etc.) into the context and then it's there forever until the conversation ends.
I like running models at home for privacy, but I also like how there are no quotas, usage isn't a worry. If the future is "loop engineering" then you will be burning through tokens and $$$ using a cloud models.
My system idles around 200W and is around 350-450W when inference load is high. Decoding (token generation) isn't all that efficient, and your GPUs sit idle more than you think during inference. Advancements like diffusion may 1) speed up decoding and 2) let you utilize more of your idle GPU.
How much does this ware out the hardware?
Also, if privacy is the main reason for running local models, why not use venice.ai and equivalent?
Probably the biggest improvement was including a backend-for-agents service definition which instructed the schema agent they were to only produce only a manifest based on the task, and to pass off that off to the next agent.
In short, I split tasks up into many pieces by defining a workflow where agents are only allowed to do very specific things before their work is passed along. This keeps them grounded and capable while also creating places for me to intervene if a workflow was say 25% or 90% successful.
Some think the human brain works similarly: thousands of mini-brain cortical columns, each with a slightly different take on the situation, voting in a majority-rules system.
Like "Here's this consumer grade GPU. Using only this GPU but with whatever models and workflow you want, see how well you can do on xyz benchmark."
Contestants would be given like 1 hour max and scored based on % of questions answered, % of questions correct and total time to finish.
Like "The Local AI challenge"
I have way too much VRAM forme such a model but Qwen never released the 122B version of Qwen3.6, which is the best class of model for my hardware. But at the same time my electricity bill is negligible, this is originally a laptop chip and it shows, it consumes almost nothing while idle and a little above 120W during prompt processing.
And Qwen3.6 has been surprisingly effective for me, I still use Clause occasionally but only for like 10% of my needs which allows me to stay well under the quota even with the cheapest plan.
Speed: ~800tps prompt processing and 50tps for token generation (with no speculative decoding).
The hardware I have (32gb Macs and a gaming PC with 10gb 3080) can only get me to Qwen3.6-35B-A3B at various quants but that’s enough (200-400 PP, 20-30 TG).
It’s taken some time to learn how to best utilize it - some things take a bit of babysitting or direction - but it’s quite useful. Not having ever used CC I can’t compare but it’s been a great assistant or pair programmer for everything from embedded C++ to Vue. I wish I could run 27B as there have been moments when this model feels like it just can’t quite figure something out but those moments are quite rare. For a lot of tasks it’s a huge time saver and has proved super capable at digging into and fixing bugs given pretty vague instructions.
I’m using Pi as my harness.
Nemotron super 3 110B works well for 1M context long vibecoding sessions
I also use Pi harness with no extension
but perhaps one individuals prompt feedback just isn't going to ever be enough I'm not sure how much you need (I know people working at big companies that have purchased in-house agents fine-tuned on internal documents etc.. and apparently these end up with bizarre behaviours not necessarily more helpful than the standard models)
I'd like to be able to essentially edit every response given by an agent and then finetune on the difference between what it produced and how I edited the text. Personally I would just remove a lot of the adjectives and try to distill the responses to core responses but I worry based on some of the work done by Owain Evans and other alignment researchers that this can sometimes push agents into tricky-to-predict tendancies.
https://cursor.com/blog/real-time-rl-for-composer
About Owain Evans work: I think he did SFT. On Twitter someone was saying that RL is not as susceptible to what he showed. I'd like to try that
but then use cheap/local model to implement the specs.
Markdown is more effective at compressing information and fits the context window easier, than hundreds of source code files
but this requires second and third passes, to smooth out the rough edges
has anyone tried that?
Results depend on the model, of course, and your computer is the limit. Mine wasn't up to the task, unfortunately.
I've been working on an ops style tool for local LLM inference. Proxying, api keys, request logging, model rewriting and much much more.
https://github.com/ndom91/llama-dash
There's apparently a reason Sonnet and Haiku have been left in previous version #s.
Still encouraging, though, that things are catching up. We can't expect $20k local setups to match $20bn compute clusters.
It's also annoying that OpenCode doesn't even try to support local LLMs properly.
Getting OpenCode to work is possible, but extremely manual and clunky to configure. I have written a script to automate converting my llama-server configs into an OpenCode config, and that helps, but it's not ideal.
I have seriously considered writing Yet Another Coding Harness in my free time. I have some ideas for what would make it nice.
I've used the cli agents for claude, cursor, and pi, plus several custom harnesses I've written myself from time to time as experiments (and I guess technically gastown, if we're calling that a harness).
Pi is... just fine.
It does what I need it to, has a decent selection of tooling out of the box, integrates nicely with other tools, and generally gets out of my way enough that I don't think about it much anymore.
If you can run ~30b models at decent speeds, I think most folks would be pleasantly surprised at how capable they are with pi.
Tack on some of the extensions (ex https://pi.dev/packages/pi-mcp-adapter?name=mcp and https://pi.dev/packages/pi-web-access?name=search) and I get web tooling (ex - perplexity search), access to mcps to do things like drive chrome (https://browsermcp.io/) or firefox (https://github.com/mozilla/firefox-devtools-mcp)
It's fine. Is it as good as a subsidized top tier model? Nope. Is it free and still very capable? Yup.
And personally, I've been having a LOT of fun with the pi sdk (https://pi.dev/docs/latest/sdk)
Which is something that all the other providers charge you api access rates for (ex - thousands a month).
But yes - it expands a lot if you're willing to play with it.
I'd actually say the vscode comparison is wrong, because vscode is very much "bring your own extension" in the same way that Pi is. While Claude is much more "visual studio" vibes. It's thick, it's opinionated, and it's absolutely not something you can really customize, but it can feel slick for supported workflows.
67M Ouput 51M Input
Total $0.83 dollar.
I honestly don't understand why people just don't use DeepSeek.
[1] https://huggingface.co/LiquidAI/LFM2.5-1.2B-Instruct
Like "Here's this consumer grade GPU. Using only this GPU but with whatever models and workflow you want, see how well you can do on xyz benchmark."
Contestants would be given like 1 hour max and scored based on % of questions answered, % of questions correct and total time to finish.
Like "The Local AI challenge"
I'm waiting to swap out my last gen Intel iMac with a new M5 mini of some kind, with the eye to hopefully be able to run some models locally. I envision a mini (heh) arms race to simply swapping out an M(X-1) for an M(X) annually as this field shakes out.
Some of the benchmarks appear to back this up [0]
Of course, a lot depends how you are using it (inference parameters, harness, prompting, etc.), but the model is quite important too.
[0]: https://artificialanalysis.ai/models/open-source/small?model...
Of course, you have to have the right hardware to be able to run with a context window like that, as it takes about 100GB of memory on my DGX Spark to do that with full f16 KV cache on the q4_k_xl model.
It’s slower but you can run them.
I mostly use it as a google search if I forget a thing, or doing the boilerplates.
I am using a mix of a non harness chat for the reply speed, and opencode / vim-ai for my boilerplates.
$0.00 / month. That's the budget.
I did just publish a free to read online book "The Rise of Local Coding Agents" [1] where I document my setup that I enjoy using. I use little-coder (built on pi) and have good results for small Python and TypeScript applications. I struggle getting good results with Common Lisp and Clojure.
For me, the problem with all local LLM-basic coding agents is slow runtime.
[1] https://leanpub.com/read/local-coding-agents
https://medium.com/p/f237d575e861
I considered investing in better hardware but doing the math, it is cheaper for me to pay for DeepSeek (yeah, I know not everyone can do that).
Then I give it to local LLM (eg: Qwen / Gemma 4) via CLI. This is possible through usage of llm-mlx on Mac (or ollama on any machine given sufficient on hardware) which serve OpenAPI endpoints compatible for Aider (CLI) or Visual Studio Code to vibe along with the agentic coding assistant.
The paid products have an advantage but are not necessary if you don't mind to be more-involved with the process and have low expectations.
My Homelab AI Dev Platform
https://news.ycombinator.com/item?id=48542433
Also,the lack of enterprise tooling to help selected an appropriate model and tooling to run a local LLM does not help.
Runs through Pi with a custom prompt (basically "don't speculate blindly, isolate things, make them traceable and measurable, then verify") and behind a pretty restrictive bwrap setup - RO bind everything other than ~/.pi, cdw and a separate tmpfs, unshare almost everything other than the network - for which I use a network namespace that only allows tcp connections to a specific ip and port (i.e the inference mac) - i.e. netns exec into bwrap.
Can't compare it to SOTA or higher-requirements models on what I work on - policy. That said, on a bunch of test pieces - it obviously isn't gpt-5.5, it definitely lags behind k2.6/glm/ds4-pro, but it absolutely is usable. Of course, on such codebases, forget about one-shotting or trusting it blindly or anything of the sort - you ask it, guide it, restart the context from time to time to have a "fresh dice roll" and to keep the context small and clean, etc. Compared to anything smaller (incl. all the usual local qwen models) - on a test piece, it figured out that memfd and mmap were used for setting up a ring buffer with natural wraparound handling (double mapping the first page at the end) and didn't tell me "this is for sharing memory between processes" or some other BS.
Performance as described in the tables in the readme here: https://github.com/antirez/ds4 ...with a bit less than half that at "low power" (30w). Both are usable.
Hardware:
- GPU: AMD 7900xtx, 24gb vram
- CPU: AMD 5950x, AM4
- RAM: 64gb DDR4 3600
Software:
- OS: Bazzite (atomic fedora - this machine is running Steam "big picture" mode on my TV when not in use for LLM tasks)
- Virtualization: Podman Quadlets, which allows me to run container images as managed systemd units
- Network: tailscale
- Inference: llama.cpp vulkan (better performance than ROCM, though I'm keeping an eye on it in the future)
- LLM API surface: llama-swap (running as a podman quadlet exposed via tailscale svc) allows running multiple models on a single endpoint.
- Web/Chat Access: open-webui (running as podman quadlet exposed via tailscale svc) allows me to access any of the models I'm using for coding harness access for chat/general purpose queries via web browser. I also have the "conduit" app for my iPhone that allows me to hit the same models from my phone.
Models:
- Qwen3.6-27B-MTP-UD-Q4_K_XL.gguf - Unsloth Q4 quant of the qwen 3.6 27B model weights, with MTP enabled. MTP is important as it improves the speed the model can run at.
- Qwen3.6-35B-A3B-UD-Q4_K_XL.gguf - Unsloth Q4 quant of 35B-A3B. Not MTP right now because I was having some issues with it?
- gemma-4-26B-A4B-it-UD-Q4_K_XL.gguf - Gemma 4, which I use sometimes via open-webui instead of Qwen, but I generally think Qwen does a better job
Flags (specific for Qwen 27b, since that's primary model):
- `-ngl 99` offload all layers to GPU
- `-c 80000` 80K context window. I'd like this to be higher, but since my GPU also has to run the desktop session for the machine, I need to leave some VRAM overhead to keep the desktop from OOM-ing
- `-np 1` single slot (no parallel request handling)
- `--no-context-shift` error instead of silently sliding the context window when full
- `--cache-reuse 256` reuse cached prefix in chunks of 256 tokens (prompt cache)
- `-b 2048` logical batch size (tokens per submission)
- `-ub 1024` physical micro-batch (per GPU pass)
- `--cache-type-k q8_0 --cache-type-v q8_0` symmetric 8-bit K/V cache. Q8 is as low as I've been able to go without getting some issues with tool calling
- `-fa on` flash attention
- `--spec-type draft-mtp` use the model's built-in MTP as the draft model
- `--spec-draft-n-max 3` propose up to 3 draft tokens per step
- `--spec-draft-n-min 0` allow zero drafts if confidence is low
- `--spec-draft-type-k q8_0 --spec-draft-type-v q8_0` KV quant for the draft path
- `--reasoning-format deepseek` parse <think> blocks in proper format
- `--chat-template-kwargs '{"enable_thinking": true}'` turns on Qwen's thinking mode on by default (clients can override)
- `--jinja` use the GGUF's Jinja chat template
- `--temp 0.6` moderate randomness (Qwen recommended value for coding)
- `--top-p 0.95` nucleus sampling (Qwen recommended value for coding)
- `--top-k 20` top-20 candidates (Qwen recommended value for coding)
- `--min-p 0.0 disabled (Qwen recommended value for coding)
Performance (27b, primary model):
- ~65t/s for token generation
- ~600 t/s for prompt processing.
- If these numbers don't mean much to you, perceptually this feels about on-par with cloud model speed, maybe slightly faster.
- ~30s cold start when swapping from a different model or starting up session from idle via llama-swap.
I have llama-swap set up to unload the model after 10 min of idle, because I sometimes use this machine for gaming as well. A little annoying, but a small price to pay to be able to use the machine for other stuff (gaming) when I'm not using it with coding tasks.
CLI/Harness:
- Crush harness (https://github.com/charmbracelet/crush) less feature rich than Claude Code, but with a smaller system prompt and better built-in LSP support. I point it at the tailnet DNS (https://llama.<tailnet>:<port>)
- Headroom (https://github.com/chopratejas/headroom) to maximize the 80k context window
- Exa MCP for web search (https://exa.ai/) this alone makes the model far more useable. It's shocking how often the official claude code or codex harness get botblocked on web fetches, and the results of a good web fetch can be the difference between a good turn and a bad turn.
A lot of people get hung up on whether Qwen 3.x models are "as smart as" some parallel Anthropic model. Most people seem to agree it's somewhere between Haiku 4.5 and Sonnet 4.5. Personally, I think the biggest thing that makes the Qwen 3.x series of models _feel_ good to use for coding workflows is that its the first time that tool calling actually works consistently on local models. If tool calling is busted even 5% of the time, it can totally ruin the flow. I think that's also why people tend to say the "harness is more important than the model" or whatever. I have a few other models set up but 27B with MTP is the best compromise of speed and quality that I've found.
This setup works well enough for me that I dropped my personal Claude Code subscription. At work I'm still using frontier models, but personally I don't feel like I need that much power for anything I work on in my personal life. I'm "lucky" that I made the random financially unwise choice to buy a 7900XTX in late 2022 for $1k as a gaming card. I had no clue it would actually be a pretty decent LLM card 3-4 years later.
Edit: sorry for the horrible formatting, I always forget that HN doesn't actually do markdown :(
I think it also helps that I'm using my machine to do home server stuff. It excels at all of the traditional workloads. Then I can lean on the AI to help with automation here and there. I find it deeply satisfying.
Sure, you can get the local models to generate plausibly-looking code for simple cases. But compared to how I solve complex design problems in a large codebase with Claude Code and Opus/Fable, this isn't worth my time.
I'm still optimizing it (with claude, to be clear), but my testing is very encouraging. I worry a lot about companies (and the government) controlling access to machine intelligence, so local is the way to go.
Disclaimer: I am a Linux infra/k8s guy, I write production code but it's mainly glue code and mainly in golang.
Addendum: most value we get is from "document intelligence" and that's all Gemma and Qwen on H100/H200
For months I spent time curating the AI+harness+skills+MCP servers, but now mainly just code with it. I find myself not bothering to use Claude (but keep paying "just in case").
That's feasible in part because my prompts have very specific objectives, constraints, and suggested staging, because I want the code to be exactly as I would write it, and I want to weigh in at specific moments. I would say the speed-up is 2-4X instead of the 10X of vibe-coding greenfield projects. The problem is not the coding speed, but building something complicated that's also correct and flexible (i.e., a directional accuracy). E.g., the agents help with abandoning a less-fruitful API shape instead of sticking with what works in a local maxima.
One flaw there is that I'm still writing code that feels clean to humans, which now is probably a waste. LLM's might be happier with 10+ parameters on one API instead of a plethora of configuration objects and convenience wrappers.
Like how we've had SETI at Home, Folding at Home, BitTorrent etc. People are clearly willing to donate their computer resources to distributed projects.
Maybe in a dAI network anyone could submit content for training on, and each user running a "node" could have their own custom private conditions on which type of content to accept for training or inference.
Like someone who dislikes anime could say "never accept anime related content or queries" so their node would basically opt-out from any data or questions about anime.
(TLDR; Distributed compute for models will require hardware at a level only really possible with data-centers at the moment.)
Token generation operates at such a scale to demand enough from a single GPU as it will often saturate the bandwidth capabilities of consumer grade interconnects like PCIe. Which fundamentally implies that distributing a model's compute across vast distances is too much of a challenge without significant infrastructure.
To give an example, When we split a model's compute between two seperate cards on a single workstation, this doesnt mean we end up with 2x the compute bandwidth for a model. Instead the increase becomes something small like 20% depending on model, because the inconnects (PCIe on consumer hardware) will quickly become so saturated with data being copied between the two GPUs so as to become a bottleneck. And remember that this is something that happens locally with PCIe, which (depending on generation) will cap out at around 20-35 GB/s depending on the generation of motherboard.
Model performance is very much tied to having the fastest and highest bandwidth single card available so as to keep data transfer operations to a minimum as the sheer volume of data necessary for the model to run is immense. I simply cant imagine how slow and unusable a model would be if the copy operations necessary for its compute needed to be performed over unreliable network speeds where there will be significant performance loss as network speeds are not reliably distributed across the globe, and their unreliable nature would demand increased overhead due to data verification.
The dream of distributed AI is a ways off.
if youre shoopping for a new pc, very easy to justify 128gb vram
Recommended setup: plenty of nutrients, some caffeine and a quiet environment.
Performance - not currently measured in tokens: roughly average.