DeepSeek-V4.1-Flash on one Apple M5 Ultra 512GB: steady 101 tok/s decode up to 256K context

HankYeomans · x · 2026-11-21

TheDavidTai reports local inference of DeepSeek-V4.1-Flash-1017 on a single Apple M5 Ultra (512GB unified memory), breaking 100 tok/s after basic tuning:

He expects far more optimizations ahead, showing 512GB unified-memory Macs can now serve large MoE models comfortably.

Original post →

More from Infra

Infra channel →