Apple M6 leaks claim 4.8x faster LLM inference, local 70B model support

kimmonismus · x · 2026-08-25

Leaks suggest Apple is preparing M6 and M5 Ultra chips for a "big leap in AI compute."

M6 Key Specs:

M5 Pro: Specifications scale even higher.

Impact: Capable of running quantized 70B-class models locally.

Related event: Rumor: Apple M6 Gets Dual Neural Engines for Big AI Boost(2 posts)→

Original post →

More from Embodied

Embodied channel →