M5 Ultra rumored with 1.2TB/s bandwidth, beating API speeds for local LLMs

StefanoGogioso · x · 2026-08-26

Rumors suggest the 512GB M5 Ultra, shipping in October, will feature 1.2TB/s memory bandwidth, a 50% increase over M3 Ultra. By stacking 4x M5 Ultra units, users may run models like Kimi K3 and GLM 5.3 locally at speeds exceeding 100 tok/sec, outperforming API calls. Based on extrapolations from M3 Max, the M5 Ultra is expected to deliver 110 TFLOPS (dense fp16).

Related event: Apple Unveils M5 Ultra and First 2nm M6 Chip, Doubling Down on On-Device AI(9 posts)→

Original post →

More from Infra

Infra channel →