← Back to community benchmarks

Qwen3.6-27B-oQ8-mtp

M2 Max (38c) · 96 GB · 8bit · 2026-05-16

Performance

32k

tokens

104.4

PP tok/s

14.9

TG tok/s

313733

TTFT (ms)

34.6

Peak mem (GB)

Hardware

Chip M2 Max (38c)

Memory 96 GB

GPU Cores 38

Software

oMLX v0.3.9.dev2

macOS macOS 26.4.1

Context 32,768