Re:M3 Macs: there's more to performance than counting cores
by stevenhuang on Saturday November 04, 2023 @02:33AM
(#38138683)
It's very exciting in the local LLMs space, where the unified memory allows fast inference of large models.
Re:M3 Macs: there's more to performance than counting cores
by dagaci on Saturday November 04, 2023 @09:59AM
(#38141049)
I read that the bandwidth is 50% lower on the M3 combined with a lower CPU core coun. This reduction will impact inferrence performance.
It maybe better to stick with M2 series if you really really think spending $10k on a laptop mac to do inferrence slowly (but faster than a plain PC of course) make sense.
Apple Silicon is amazing. But if you’re doing heavy GPU it’s not very exciting.