Indeed! Also, Mixtral 8x7b runs just as well on older M1 Max and M2 Max Macs, si... | Hacker News

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

		woadwarrior01 on March 23, 2024 \| parent \| context \| favorite \| on: Emad Mostaque resigned as CEO of Stability AI Indeed! Also, Mixtral 8x7b runs just as well on older M1 Max and M2 Max Macs, since LLM inference is memory bandwidth bound and memory bandwidth hasn't significantly changed between M1 and M3.

karolist on March 23, 2024 [–]

It didn't change at all, rather was reduced in certain configurations.

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