← Back to community benchmarks

Qwen3.6-27B-MXFP4-MTP

M1 Max (24c) · 64 GB · 4bit · 2026-05-14

Performance

1k

tokens

69.7

PP tok/s

14.4

TG tok/s

14702

TTFT (ms)

15.1

Peak mem (GB)

Hardware

Chip M1 Max (24c)

Memory 64 GB

GPU Cores 24

Software

oMLX v0.3.9.dev2

macOS macOS 26.3.1

Context 1,024