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

The GGUF quantisations do run on most recent hardware, albeit at increasingly concerning quality tradeoffs.


I haven't noticed any quality degradation with the 8-bit GGUF for Flux Dev, but I'm sure the smaller quantizations perform worse.




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

Search: