← Back to community benchmarks

Qwen3.6-27B-MXFP4-MTP

M4 Max (32c) · 36 GB · 4bit · 2026-05-15

Performance

128k

tokens

117.5

PP tok/s

15.8

TG tok/s

1115469

TTFT (ms)

31.6

Peak mem (GB)

Hardware

Chip M4 Max (32c)

Memory 36 GB

GPU Cores 32

Software

oMLX v0.3.8

macOS macOS 15.3

Context 131,072