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

Depends on which model. I haven't bothered doing it on my 8GB because the only model that would fit is the 7B model quantized to 4 bits, and that model at that size is pretty bad for most things. I think you could have fun with 13B with 12GB VRAM. The full size model would require >35GB even quantized.


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

Search: