Comment by turnsout 9 months ago I believe mlx will allow you to run the models marginally faster (per a recent blog post by @simonw) 3 comments turnsout Reply simonw 9 months ago 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! indigodaddy 9 months ago I for one, am willing to just trust you bro ;) turnsout 9 months ago Yeah I’ll go with Simon’s vibes over most people’s measurements!
simonw 9 months ago 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! indigodaddy 9 months ago I for one, am willing to just trust you bro ;) turnsout 9 months ago Yeah I’ll go with Simon’s vibes over most people’s measurements!
indigodaddy 9 months ago I for one, am willing to just trust you bro ;) turnsout 9 months ago Yeah I’ll go with Simon’s vibes over most people’s measurements!
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!