This is a good idea. What setup do you use and how does the model perform? | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		markus_zhang 4 days ago \| parent \| context \| favorite \| on: Ask HN: Can you cut off AI usage immediately? This is a good idea. What setup do you use and how does the model perform?

		help

cyanydeez 4 days ago [–]

AMD 395+ w/128B. Qwen3-coder-next running from llama.cpp; opencode seems to have the best depth. It can get to around 80k context before pooping out.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact