← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

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

Performance

32k

tokens

112.5

PP tok/s

12.8

TG tok/s

291333

TTFT (ms)

22.5

Peak mem (GB)

Hardware

Chip M4 Max (32c)

Memory 36 GB

GPU Cores 32

Software

oMLX v0.3.9.dev2

macOS macOS 26.4.1

Context 32,768