← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M4 Max (40c) · 128 GB · 4bit · 2026-05-09

Performance

32k

tokens

228.0

PP tok/s

32.8

TG tok/s

143750

TTFT (ms)

22.6

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.9.dev1

macOS macOS 26.4.1

Context 32,768