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

Language models range from 1 to 300+ GB when loaded. It depends on how you load them, if you load in int8 you get 4x reduction.


Consider applying for YC's Winter 2026 batch! Applications are open till Nov 10

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

Search: