← Back to community benchmarks

Qwen3.6-27B-oQ6-mtp

M4 Max (40c) · 64 GB · 6bit · 2026-05-19

Performance

1k

tokens

236.3

PP tok/s

20.8

TG tok/s

4334

TTFT (ms)

22.6

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.3.9rc1

macOS macOS 26.5

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	236.3	20.8	22.6 GB	current
4k	244.1	20.4	24.0 GB	view
8k	242.5	19.9	25.1 GB	view
16k	236.2	19.2	26.6 GB	view
32k	222.6	17.8	29.6 GB	view