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

If you're talking about 3.3 70B Q4, any PC with 64 GB RAM could run it.


I can use RTX to speed the inference up. My budget is up to $2500.


Maybe you could run some layers on a 3090; I'm not sure how much speedup it would give.




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

Search: