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

Sadly, there is no way to tell if this is running with real weights or being heavily quantized.
 help



just checked, yes they don't seem to provide that information, most other providers are advertising fp8 or fp4 which is okay, but "together" doesn't, so they are likely using fp4



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

Search: