← Back to community benchmarks

Qwen3.6-27B-oQ6-fp16-mtp

M2 Max (30c) · 64 GB · 6bit · 2026-05-21

Performance

1k

tokens

146.6

PP tok/s

17.6

TG tok/s

6985

TTFT (ms)

23.0

Peak mem (GB)

Hardware

Chip M2 Max (30c)

Memory 64 GB

GPU Cores 30

Software

oMLX v0.3.9

macOS macOS 26.5

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	146.6	17.6	23.0 GB	current
4k	151.4	17.5	24.4 GB	view
8k	150.4	17.4	25.4 GB	view
16k	146.5	15.8	26.9 GB	view
32k	138.8	15.0	29.9 GB	view