← Back to community benchmarks

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

M2 Max (38c) · 96 GB · 4bit · 2026-05-20

Performance

16k

tokens

186.4

PP tok/s

25.4

TG tok/s

87906

TTFT (ms)

20.7

Peak mem (GB)

Hardware

Chip M2 Max (38c)

Memory 96 GB

GPU Cores 38

Software

oMLX v0.3.9rc1

macOS macOS 26.4.1

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	189.2	28.8	16.7 GB	view
4k	194.5	28.0	18.2 GB	view
8k	193.3	26.6	19.2 GB	view
16k	186.4	25.4	20.7 GB	current
32k	177.2	23.3	23.7 GB	view