← Back to community benchmarks

Qwen3.6-27B-oQ4-fp16-mtp

M1 Max (24c) · 32 GB · 4bit · 2026-05-20

Performance

8k

tokens

114.3

PP tok/s

14.6

TG tok/s

71663

TTFT (ms)

18.9

Peak mem (GB)

Hardware

Chip M1 Max (24c)

Memory 32 GB

GPU Cores 24

Software

oMLX v0.3.9rc1

macOS macOS 26.4.1

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	112.6	15.4	16.9 GB	view
8k	114.3	14.6	18.9 GB	current
32k	105.6	14.6	23.3 GB	view