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

471–480 of 620 posts

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

#471

Post by hparadiz »

bandrami wrote: post #461
hparadiz wrote: post #459

Earlier quoted context omitted.

Yea there's something called a phone book too.

And that would be a much better source for a phone number than Googling. Similarly, the docs that ship with software are a better source for command line switches for that software than a search engine or LLM.

My lived experience right now is a lot of super talented people around me using these tools all day every day to build awesome things and then there's the randos like you on HN who think they know better. Protip: You don't know squat.

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

#472

Post by cloudengineer94 »

I have tried in both my Mac and my desktop (Rtx 5090) with Gemma 4 and Qwen and so far nothing is quite replacing Claude Code or Kiro for spec driven architecture & development.

I do think we are slowly getting Gemma 4 was a big jump

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

#473

Post by mbitai »

LoganDark wrote: post #219
chakspak wrote: post #173

Earlier quoted context omitted.

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?

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)

I've also had good results with Pi, and I got used to the new workflows without subagents, MCP, etc.

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

#476

Post by underdeserver »

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…

Nit - it is not completely free.

You are paying for the extra power draw.

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

#477

Post by deepvibrations »

The TLDR is that the best setup is probably Mac Studio (128GB RAM) / MacBook (36GB) with Qwen 3.6 35B (3B active params), or Qwen 3.5 122B model (this one is slow though).

These models are still very capable with good hardware, but they do lack the deep reasoning of major models and require more precise prompting.

So unless you really need the privacy, or have a lot of excess cash, it is not recommended, as considering the price of major models, it's just extremely cost inefficient!

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

#478

Post by NamlchakKhandro »

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…

Thinking Claude is leading edge... I really think you need to re-evaluate what you research you think you're doing.

Claude Code is not Claude Opus/Sonnet/Haiku.

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

#480

Post by luipugs »

secult wrote: post #429
luipugs wrote: post #424

Earlier quoted context omitted.

Don't you read through all the output of the agent before committing them?

That's not the way how human brain works.

I'm not getting it. OP said they are wary of letting the agent make choices for them, and outsourcing those choices lessens their understanding of them. They could interrogate the agent on why those choices were made until they have sufficient understanding, and they can also change the solution if they want to.
Post reply on HN