Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?

news.ycombinator.com

Post reply on HN
Print view View original

321–330 of 620 posts

Re: Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?

#321

Post by storus »

jacobgold wrote: post #62
pierotofy wrote: post #36

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/

"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.

You can already get Opus 4.6 level of performance on subtasks with some local models. So you need to pick a proper code writer, plan writer, code tester etc. model that matches your target expectations and use a coding tool that allows calling different LLMs for different subtasks. For example, people use StepFun 3.x or DeepSeek4-Flash for planning, Qwen3.6-27B for coding.

Re: Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?

#323

Post by jkells »

lambda wrote: post #290
computerex wrote: post #192

Earlier quoted context omitted.

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.

Which Opus? Anthropic has been releasing models named Opus since 2024 with Claude 3 Opus. Opus has gotten vastly more capable since then. Local model far surpass Opus 3. They even surpass Opus 4 on most benchmarks. Sure, if you compare to the latest Opus 4.8 or even 4.6, they're not there yet. But there's a huge difference in performance between 4 and 4.8.

Can't speak for anyone else but there was a step change in frontier models last November. Opus 4.5 and GPT 5.2 I think.

When I colloquially say Opus level I really mean Opus 4.5 or later

Re: Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?

#324

Post by XCSme »

_bobm wrote: post #318
XCSme wrote: post #309

Earlier quoted context omitted.

> You will notice multiple "thinking" parts per "turn" I thought that was the code harness simply minifying the outputs. Many models now no longer return the entire chain-of-thought (to avoid distillation attacks). So yes, we don't get the raw LLM output, but I think it's just the thinking summarized, not a complex orchestration or different models. I do agree though that now cloud models are kind of a black box, tha…

idk what is "minifying outputs" in the context of what we are talking about. Opencode is opensource, you can find out what it is doing. Last time I checked, OpenAI even send (in the response) the summary of the thinking part alreafy in markdown, so opencode has to remove the formatting to format it to their liking. > Many models now no longer return the entire chain-of-thought (to avoid distillation attacks). This is…

So, are you saying that local models are maybe better than we give them credit? Because with some extra orchestration/processing we could improve the results?

Re: Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?

#325

Post by leptons »

ux266478 wrote: post #74
leptons wrote: post #25

Earlier quoted context omitted.

Have you measured your electricity consumption for this rig? I have to wonder how much it would cost you per month.

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.

I'm paying about $0.19/hr and using half that power just for a large spinning RAID, running some VMs and security cameras. And I'm reconsidering my digital extravagance because of the electric bill. You probably make way more money than I do.

Re: Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?

#326

Post by lambda »

jkells wrote: post #323
lambda wrote: post #290

Earlier quoted context omitted.

Which Opus? Anthropic has been releasing models named Opus since 2024 with Claude 3 Opus. Opus has gotten vastly more capable since then. Local model far surpass Opus 3. They even surpass Opus 4 on most benchmarks. Sure, if you compare to the latest Opus 4.8 or even 4.6, they're not there yet. But there's a huge difference in performance between 4 and 4.8.

Can't speak for anyone else but there was a step change in frontier models last November. Opus 4.5 and GPT 5.2 I think. When I colloquially say Opus level I really mean Opus 4.5 or later

Right. Local models haven't quite hit that level yet. The biggest open models, which you need tens of thousands of dollars of hardware to run at reasonable speed, have pretty much hit that level of capability, but most models you can reasonably run at home aren't quite there yet. But given the gap, if local models keep improving, you'd expect to maybe see that level by this November.

Re: Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?

#327

Post by klardotsh »

timmit wrote: post #310
Greenpants wrote: post #112

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 interestin…

I got a 48GB Ram MacBook, somehow I cannot even run a 20b model, I was suprised that you get 35b model locally.

4-5 bit quants would probably fit pretty well on your rig. Check HuggingFace for Qwen3.6-35B-A3B-MTP-GGUF [1]. They've also got a cool UI thing these days to help indicate which quants of a model will run on your hardware.

Full octane isn't gonna fit on much of anything south of a 128GB machine once adding KV cache.

[1]: https://huggingface.co/unsloth/Qwen3.6-35B-A3B-MTP-GGUF

Re: Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?

#328

Post by disqard »

ojr wrote: post #315
Greenpants wrote: post #112

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 interestin…

I can use Gemini 3 Flash with the harness I built for around 8 years and still not exceed the cost of a Mac Studio with 128GB, the price for privacy is very high. Agentic flows that get stuck can be worked around but I prefer developer velocity.

Under-rated take, thanks for stating this!

Not everyone can plough $$$$ into hardware right now (more power to those who can), so choosing to rent is an A-Ok strategy.

Re: Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?

#329

Post by geophile »

Greenpants wrote: post #112

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 interestin…

My experience is almost identical. I have found that I need to be very careful with planning, breaking things down into small isolated steps (I can have qwen do this); and also (me) writing a very clear design. Relying on qwen to fill in a lot of those precise details results in those about-to-write loops.

Yeah, that edit inability is weird. I’ve updated AGENTS.md to limit editing (as opposed to rewriting) and that helps a little.

Re: Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?

#330

Post by driverdan »

rootlocus wrote: post #100
horsawlarway wrote: post #49

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…

2x RTX3090 are around $4400. Without any electricity costs or other parts, that's 3.6 years of $100/m claude.

If you pay $2200 for a 3090 you're a sucker. They're not worth anything close to that.
Post reply on HN