← Back to community benchmarks

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

M2 Max (38c) · 96 GB · 4bit · 2026-05-08

Performance

16k

tokens

189.4

PP tok/s

25.6

TG tok/s

86513

TTFT (ms)

20.7

Peak mem (GB)

Hardware

Chip M2 Max (38c)

Memory 96 GB

GPU Cores 38

Software

oMLX v0.3.9.dev1

macOS macOS 26.4.1

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	188.8	26.2	16.8 GB	view
4k	195.9	28.6	18.2 GB	view
8k	194.5	26.6	19.2 GB	view
16k	189.4	25.6	20.7 GB	current
32k	177.3	12.8	23.7 GB	view