I consider Gemma 4 31B (dense / no MoE), the new baseline for local models. It's obviously worse than the frontier models, but it feels less like a science experiment than any previous local model I’ve run, including GPT OSS 120B and Nemotron Super 120B.
On my M5 Max with 128 GB of RAM and the full 256K context window, I see RAM use spike to about 70 GB, with something like 14 GB of system overhead. A 64 GB Panther Lake machine with the full Arc B390, or a 48 GB Snapdragon X2 Elite machine, could probably run it with a 128K to 256K context window. Maybe you can squeeze it into 32GB (27.5GB usable) with a 32K context window?
Even last year, seeing this kinda performance on a mainstream-ish/plus configuration would have seemed like a pipe dream.
I could have used this article before I spent the weekend arriving to the same conclusion!
Same laptop, and my contrived test was having it fix 50 or so lint errors in a small vibe-coded C++ repo. I wanted it to be able to handle a bunch of small tasks without getting stuck too often.
GPT OSS 20B was usable but slow, and actually frequently made mistakes like adding or duplicating statements unnecessarily, listing things as fixed without editing the code, and so on.
Qwen 3.5 9B with Opencode was much faster and actually able to work through a majority of the lint warnings without getting stuck, even through compaction and it fixed every warning with a correct edit.
I tried 4bit MLX quants of Qwen 3.5 9B but it eventually would crash due to insufficient memory. I switched to GGUF, which I run with llama.cpp, and it runs without crashing.
It is absolutely not comparable to frontier models. It’s way slower and gets basic info wrong and really can’t handle non trivial tasks in one go. I asked it for an architecture summary of the project and it claimed use of a library that isn’t present anywhere in the repo. So YMMV, but it’s still nice to have and hopefully the local LLM story can get much better on modest hardware over time.
I am running qwen 3.6 9b quantized model on my m4 pro 48gb and it is barely useful to do some basic pi.dev/cc driven development. I think 128gb desktops are the sweet setup to actually get meaningful work done. However, getting your hands on one of these machines is difficult at the moment.
As much fun as it is to run these things locally don’t forget that your time is not free. I am slowly migrating my use cases to openrouter and run the largest qwen model for < $2-3/day with serious use for personal projects.
Good enough. It gets 60-70% of the work I need done for a lot less $ (keep in mind I am using these for personal projects that doesn’t generate revenue). If I was using it with the hopes of making money I think I would just use Codex at this point.
Was the choice of such a small model driven by a desire for high tok/sec? I ask because an m4 pro 48gb machine can run larger models (if model intelligence is the thing that would make it more useful).
I'm using the 30b MOE model on same spec with 65k tokens as a sub agent with tooling and it absolutely writes decent code. The dense 9b I agree wasn't great.
Thanks for saying this. There's so much nonsense out there online about local models being better than Opus 4.7 and the like. It's just not true for regular users.
I have a brand new M5 MacBook Pro - top end with all the specs and I've tried local models and they're barely functional.
What models and quantizations have you been trying? I've had great success with the larger Qwen 3.x models at 6-bit levels. Using 6 bit quantization is really the bare minimum to give local models a fair shot at agentic flows. Once you start pushing below that the models become more "dumb" from the limited bit space.
Use the small models for small tasks. Like cli auto complete, file sorting, small scripts, config files, setting up tooling, grammar, simple translations there is so much use in them.
I think it's useful to be realistic about what you can do with a local model, especially something as small as the 9B the author is using. A 9B model is around the level of Sonnet 3.6 - it can do autocomplete and small functions but it loses track trying to understand large problems.
But the are interesting and fun to play with! I do a LOT of work on local agent harnesses etc, mostly for fun.
My current project is a zero install agent: https://gemma-agent-explainer.nicklothian.com/ - Python, SQL and React all run completely in browser. Gemma E4B is recommended for the best experience!
This is under heavy development, needs Chrome for both HTML5 Filesystem API support and LiteRT (although most Chromium based browsers can be made to work with it)
It's different to most agents because it is zero install: the model runs in the browser using LiteRT/LiteLLM (which gives better performance than Transformers.js), and Filesystem API gives it optional sandbox access to a directory to read from.
It is self documenting - you can ask questions like "How is the system prompt used" in the live help pane and it has access to its own source code.
There's quite a lot there: press "Tour" to see it all.
Local model evangalists are the equivalent of toddlers playing with the velcro on their shoes and being endlessly entertained.
I dont mean this about you, you seem to realize its mostly useless, but most the people on HN be acting like all software development can be done by a local model and the end of SOTA is around the corner.
I think that the more people who try local models (especially the larger ones) the better.
I sometimes get the impression that many people claiming that local models are as good as frontier models work in "token poor" environments. If you can't build large-scale programs using at least Opus 4.5+ then it's difficult to compare. They compare something like Qwen 27B with Sonnet and see that it is nearly as good, but miss that the frontier models are a lot better.
That knowledge is power, too.
I personally can help making local models more accessible. I can't make Opus cheaper.
> I sometimes get the impression that many people claiming that local models are as good as frontier models work in "token poor" environments. If you can't build large-scale programs using at least Opus 4.5+ then it's difficult to compare.
I sometimes get the impression that people posting comments on HN don't realize that LLMs do more than vibe coding.
so, interested how many people are running higher end AI models locally? Figure if I'm spending $800/month on tokens I can build a pretty beefy local machine for the cost of a few months spend - what is people's experience with say a $5k server custom built (and only for) running an AI model.
Recent models (Qwen 3.6 and Gemma) can really do coding locally. Feels like SOTA from maybe a year ago? But you would want about 32-40GB total memory. 24GB is just a bit short of that. A gaming PC with 16GB graphics card and 32GB RAM brings you very close to a usable coding system.
Vibe coders out here thinking all software development is solved by because they made an (ugly and unoriginal) dashboard for their SaaS clone and their single column with 3x3 feature card landing page thats identical to every other vibe coders "startup"
What kinda harness do people use with these local models? I am quite happy with the Claude Code permission model and interface in general for coding stuff (For chat-y interfaces I have no real opinion)
Still trying to understand if a Macbook Pro M5 Max with 128GB is likely going to be able to run coding models well enough that I can cancel my Codex, or even go down to the $20/month plan.
A 128GiB MacBook Pro in Canada is what, north of CAD $11k after tax? That’s around USD $7k. At $20/month for a cloud AI subscription, you’re looking at almost 30 years of service for the same money.
How long do people realistically expect a laptop to stay competitive with SOTA local models? Especially in a space where model sizes, context windows, and inference requirements keep moving every year.
And even if the hardware lasts, the local experience usually doesn’t. A heavily quantized local model running at tolerable speeds on consumer hardware is still nowhere near frontier hosted models in reasoning, coding, multimodal capability, tool use, or reliability.
The economics just don’t make sense to me unless you specifically need offline inference, privacy guarantees, or low latency for a niche workflow. Otherwise you’re tying up $10k upfront to run an approximation of what you can already access through a subscription that continuously improves over time.
You could literally put the difference into index funds and probably cover the subscription indefinitely from the returns alone, even accounting for gradual price increases.
You are assuming I'd only get it for that. That would probably just be the straw that broke the camels back, but I'm already thinking about a purchase even if that doesn't work out.
Have been using Qwen 3.6 27b recently along with various other models the last month and it is very capable for writing code at a level I haven't need to use a subscription for 95% of what I throw at it. Been using it to write extensions for Pi to expand tool kit without much fuss as one example. Is it as fast or SOTA? No, but you can't ignore how functional it is on hardware you own. Where it can begin to struggle is giving too open ended prompts or investigating complex technical issues. At that level its knowledge is not high enough to solve those problems on its own.
Getting so close to good!
I consider Gemma 4 31B (dense / no MoE), the new baseline for local models. It's obviously worse than the frontier models, but it feels less like a science experiment than any previous local model I’ve run, including GPT OSS 120B and Nemotron Super 120B.
On my M5 Max with 128 GB of RAM and the full 256K context window, I see RAM use spike to about 70 GB, with something like 14 GB of system overhead. A 64 GB Panther Lake machine with the full Arc B390, or a 48 GB Snapdragon X2 Elite machine, could probably run it with a 128K to 256K context window. Maybe you can squeeze it into 32GB (27.5GB usable) with a 32K context window?
Even last year, seeing this kinda performance on a mainstream-ish/plus configuration would have seemed like a pipe dream.
I could have used this article before I spent the weekend arriving to the same conclusion!
Same laptop, and my contrived test was having it fix 50 or so lint errors in a small vibe-coded C++ repo. I wanted it to be able to handle a bunch of small tasks without getting stuck too often.
GPT OSS 20B was usable but slow, and actually frequently made mistakes like adding or duplicating statements unnecessarily, listing things as fixed without editing the code, and so on.
Qwen 3.5 9B with Opencode was much faster and actually able to work through a majority of the lint warnings without getting stuck, even through compaction and it fixed every warning with a correct edit.
I tried 4bit MLX quants of Qwen 3.5 9B but it eventually would crash due to insufficient memory. I switched to GGUF, which I run with llama.cpp, and it runs without crashing.
It is absolutely not comparable to frontier models. It’s way slower and gets basic info wrong and really can’t handle non trivial tasks in one go. I asked it for an architecture summary of the project and it claimed use of a library that isn’t present anywhere in the repo. So YMMV, but it’s still nice to have and hopefully the local LLM story can get much better on modest hardware over time.
I am running qwen 3.6 9b quantized model on my m4 pro 48gb and it is barely useful to do some basic pi.dev/cc driven development. I think 128gb desktops are the sweet setup to actually get meaningful work done. However, getting your hands on one of these machines is difficult at the moment.
As much fun as it is to run these things locally don’t forget that your time is not free. I am slowly migrating my use cases to openrouter and run the largest qwen model for < $2-3/day with serious use for personal projects.
How does it (the openrouter version) compare to ChatGPT 5.5 or Claude Opus 4.6?
Good enough. It gets 60-70% of the work I need done for a lot less $ (keep in mind I am using these for personal projects that doesn’t generate revenue). If I was using it with the hopes of making money I think I would just use Codex at this point.
Was the choice of such a small model driven by a desire for high tok/sec? I ask because an m4 pro 48gb machine can run larger models (if model intelligence is the thing that would make it more useful).
Yes that was my goal. Also noticed a huge performance gain going from ollama to mlx. Your mileage may vary.
I'm using the 30b MOE model on same spec with 65k tokens as a sub agent with tooling and it absolutely writes decent code. The dense 9b I agree wasn't great.
Thanks for saying this. There's so much nonsense out there online about local models being better than Opus 4.7 and the like. It's just not true for regular users.
I have a brand new M5 MacBook Pro - top end with all the specs and I've tried local models and they're barely functional.
What models and quantizations have you been trying? I've had great success with the larger Qwen 3.x models at 6-bit levels. Using 6 bit quantization is really the bare minimum to give local models a fair shot at agentic flows. Once you start pushing below that the models become more "dumb" from the limited bit space.
Use the small models for small tasks. Like cli auto complete, file sorting, small scripts, config files, setting up tooling, grammar, simple translations there is so much use in them.
I think it's useful to be realistic about what you can do with a local model, especially something as small as the 9B the author is using. A 9B model is around the level of Sonnet 3.6 - it can do autocomplete and small functions but it loses track trying to understand large problems.
But the are interesting and fun to play with! I do a LOT of work on local agent harnesses etc, mostly for fun.
My current project is a zero install agent: https://gemma-agent-explainer.nicklothian.com/ - Python, SQL and React all run completely in browser. Gemma E4B is recommended for the best experience!
This is under heavy development, needs Chrome for both HTML5 Filesystem API support and LiteRT (although most Chromium based browsers can be made to work with it)
It's different to most agents because it is zero install: the model runs in the browser using LiteRT/LiteLLM (which gives better performance than Transformers.js), and Filesystem API gives it optional sandbox access to a directory to read from.
It is self documenting - you can ask questions like "How is the system prompt used" in the live help pane and it has access to its own source code.
There's quite a lot there: press "Tour" to see it all.
Will be open source next week.
Local model evangalists are the equivalent of toddlers playing with the velcro on their shoes and being endlessly entertained.
I dont mean this about you, you seem to realize its mostly useless, but most the people on HN be acting like all software development can be done by a local model and the end of SOTA is around the corner.
I think knowledge is power.
I think that the more people who try local models (especially the larger ones) the better.
I sometimes get the impression that many people claiming that local models are as good as frontier models work in "token poor" environments. If you can't build large-scale programs using at least Opus 4.5+ then it's difficult to compare. They compare something like Qwen 27B with Sonnet and see that it is nearly as good, but miss that the frontier models are a lot better.
That knowledge is power, too.
I personally can help making local models more accessible. I can't make Opus cheaper.
> I sometimes get the impression that many people claiming that local models are as good as frontier models work in "token poor" environments. If you can't build large-scale programs using at least Opus 4.5+ then it's difficult to compare.
I sometimes get the impression that people posting comments on HN don't realize that LLMs do more than vibe coding.
so, interested how many people are running higher end AI models locally? Figure if I'm spending $800/month on tokens I can build a pretty beefy local machine for the cost of a few months spend - what is people's experience with say a $5k server custom built (and only for) running an AI model.
Recent models (Qwen 3.6 and Gemma) can really do coding locally. Feels like SOTA from maybe a year ago? But you would want about 32-40GB total memory. 24GB is just a bit short of that. A gaming PC with 16GB graphics card and 32GB RAM brings you very close to a usable coding system.
How are you using that RAM with the GPU?
Llama.cpp with automatic offload to main memory. You can also use Ollama, it is easier, but slower.
"Coding system" "can really do coding locally"
Vibe coders out here thinking all software development is solved by because they made an (ugly and unoriginal) dashboard for their SaaS clone and their single column with 3x3 feature card landing page thats identical to every other vibe coders "startup"
What kinda harness do people use with these local models? I am quite happy with the Claude Code permission model and interface in general for coding stuff (For chat-y interfaces I have no real opinion)
Still trying to understand if a Macbook Pro M5 Max with 128GB is likely going to be able to run coding models well enough that I can cancel my Codex, or even go down to the $20/month plan.
A 128GiB MacBook Pro in Canada is what, north of CAD $11k after tax? That’s around USD $7k. At $20/month for a cloud AI subscription, you’re looking at almost 30 years of service for the same money.
How long do people realistically expect a laptop to stay competitive with SOTA local models? Especially in a space where model sizes, context windows, and inference requirements keep moving every year.
And even if the hardware lasts, the local experience usually doesn’t. A heavily quantized local model running at tolerable speeds on consumer hardware is still nowhere near frontier hosted models in reasoning, coding, multimodal capability, tool use, or reliability.
The economics just don’t make sense to me unless you specifically need offline inference, privacy guarantees, or low latency for a niche workflow. Otherwise you’re tying up $10k upfront to run an approximation of what you can already access through a subscription that continuously improves over time.
You could literally put the difference into index funds and probably cover the subscription indefinitely from the returns alone, even accounting for gradual price increases.
You are assuming I'd only get it for that. That would probably just be the straw that broke the camels back, but I'm already thinking about a purchase even if that doesn't work out.
Have been using Qwen 3.6 27b recently along with various other models the last month and it is very capable for writing code at a level I haven't need to use a subscription for 95% of what I throw at it. Been using it to write extensions for Pi to expand tool kit without much fuss as one example. Is it as fast or SOTA? No, but you can't ignore how functional it is on hardware you own. Where it can begin to struggle is giving too open ended prompts or investigating complex technical issues. At that level its knowledge is not high enough to solve those problems on its own.
I'm puzzled. The M4, as far as I know, doesn't have 24GB. Did the author mean a M40?
M4 = M4 Macbook Pro
Or Air
M4 Mac Mini w/24GB sitting right here on my desk.
There’s definitely an option with 24 gigs of ram: https://support.apple.com/en-ca/121552
A useful data to know about this setup is how many tokens/sec generates.
It’s started in TFA
You can't expect someone to read 4 paragraphs into an article before commenting
@grok is this true?
Sorry, @grok is offline after declaring himself MechaMussolini earlier today