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

161–170 of 620 posts

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

#161

Post by shironnnn_ »

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.

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

#162

Post by MadrasThorn »

codinhood wrote: post #26

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 distributi…

It's great at accelerating hardware innovation however.

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

#163

Post by googletron »

augusto-moura wrote: post #141
freetonik wrote: post #114

Earlier quoted context omitted.

That's also years of top tier PC gaming, if you're into that.

2x RTX3090 is extremely overkill for gaming, you can run any released game on earth on ultra for much less

what?

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

#164

Post by jmuguy »

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.

Or a really excellent experience playing Satisfactory with the settings cranked up, which is priceless.

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

#165

Post by lambda »

GardenLetter27 wrote: post #129
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…

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?

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

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

#166

Post by flowerthoughts »

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.

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.

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

#167

Post by rvnx »

dabinat wrote: post #35

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.

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)

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

#170

Post by zozbot234 »

jmuguy wrote: post #159
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…

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.

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.
Post reply on HN