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

8 bit (and 4 bit?) quantization is low hanging fruit, assuming its not already running in 8 bit.

An 8GB requirement kinda sounds like they have already quantized the model though.



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: