← Back to community benchmarks

Qwen3.6-27B-oQ8-mtp

M4 Max (40c) · 48 GB · 8bit · 2026-05-18

Performance

4k

tokens

244.8

PP tok/s

26.3

TG tok/s

16730

TTFT (ms)

30.3

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 48 GB

GPU Cores 40

Software

oMLX v0.3.9.dev2

macOS macOS 26.4.1

Context 4,096