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

I've got an M2 Ultra with 64 GB, and I've been using gpt-oss-20b lately with good results. Performance and RAM usage have been reasonable for what I've been doing. I've been thinking of trying the newer Qwen 3 Coder Next just to see what it's like, though.


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

Search: