Comment by Grombobulous

I could believe that especially with some of the chips playing catch-up.

E.g., the M7 chip is rumored to be the one where Apple has poured really serious effort into local AI performance where previous generations seem to have mostly been coincidentally good at it.

Maybe this is an incorrect opinion but I don’t personally think that the M1-M3 or maybe M4 or even M5 chips were designed with LLM inference in mind at all. These were designed with things like video rendering, image/video ML, and rasterization performance in mind.