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.
Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?
11–20 of 620 posts
Re: Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?
#12Related: 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.
Re: Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?
#13Pretty 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.
I’d rather ask my butcher than Haiku for coding tasks
Re: Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?
#14Yes, 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.
I personally get about 50 tokens per hour.
Re: Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?
#15i 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/
Re: Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?
#16Always 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?
Re: Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?
#17This was posted shortly after your Ask HN post:
My Homelab AI Dev Platform
Re: Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?
#18Related: 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 s…
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.
Re: Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?
#19I'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…
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
Re: Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?
#20I 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.