AirLLM 70B inference with single 4GB GPU | Hacker News

new | ask | show | jobs

AirLLM 70B inference with single 4GB GPU (github.com)

163 points by Anon84 10 hours ago | 61 comments

Loading...

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

Search:

yet another Hacker News client · github.com/reiuyuu/nhn