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

Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?14 points by cloudking 1 hour ago | hide | past | favorite | 3 commentsHas anyone here fully swapped Claude/GPT for a local model as their main coding tool, not just for side experiments? If so, please share your setup and performance (e.g tok/s) help

I have an optane and lots of ram, so I tried full-fat models for writing some function overnight, as I get about 0.7 t/s. My current go-to test is to transpose a bit-matrix from one bit at a time to using avx512. the cloud models all play with that like its nothing. Kimi 2.6 and GLM 5.1 both failed miserably. Not yet, tried Gemma 4 on an Apple M4 but the tok/s is significant lower than the cloud offering.Also,the lack of enterprise tooling to help selected an appropriate model and tooling to run a local LLM does not help. Not “local” and not interactive coding but sharing since it might be helpful. I have 2x RTX Pro 6000 Blackwell running DeepSeek V4 Flash. I get 160 tok/s raw but it’s a reasoning model. For my use case, I have it auto-write code and another system auto-review the code.I occasionally use it with pi to write some code and it’s blazing fast but it’s mostly habit that keeps me with CC and Codex. Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact