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

As mentioned you can run this on a server board with 768+ gb memory in cpu mode. Average joe is going to be running quantized 30b (not 600b+) models on an $300/$400/$900 8/12/16gb GPU


I'm not sure that's enough RAM to run it at full precision (FP8).

This guy ran a 4-bit quantized version with 768GB RAM: https://news.ycombinator.com/item?id=42897205




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

Search: