← Back to community benchmarks

Qwen3.6-27BoQ4

M2 Max (30c) · 64 GB · 4bit · 2026-05-20

Performance

4k

tokens

158.5

PP tok/s

20.3

TG tok/s

25844

TTFT (ms)

17.9

Peak mem (GB)

Hardware

Chip M2 Max (30c)

Memory 64 GB

GPU Cores 30

Software

oMLX v0.3.8

macOS macOS 26.5

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	154.8	21.3	16.5 GB	view
4k	158.5	20.3	17.9 GB	current
8k	157.3	19.3	18.5 GB	view
16k	153.3	18.8	20.4 GB	view
32k	144.0	17.2	23.4 GB	view