← Back to community benchmarks

Qwen3.6-27B-mtp

M1 Max (24c) · 64 GB · 8bit · 2026-05-14

Performance

1k

tokens

67.1

PP tok/s

11.0

TG tok/s

15255

TTFT (ms)

28.3

Peak mem (GB)

Hardware

Chip M1 Max (24c)

Memory 64 GB

GPU Cores 24

Software

oMLX v0.3.9.dev2

macOS macOS 26.3.1

Context 1,024