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

I believe mlx will allow you to run the models marginally faster (per a recent blog post by @simonw)


Yeah, you don't necessarily need it but it's optimized for Apple Silicon and in my experience feels like it gives slightly better performance than GGUFs. I really need to formally measure that so I'm not just running on vibes!


I for one, am willing to just trust you bro ;)


Yeah I’ll go with Simon’s vibes over most people’s measurements!




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

Search: