← Back to community benchmarks

Qwen3.6-27B-UD

M5 Max (40c) · 128 GB · 4bit · 2026-04-26

Performance

8k

tokens

860.4

PP tok/s

20.1

TG tok/s

9521

TTFT (ms)

27.3

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.6

macOS macOS 26.4

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	771.8	21.2	25.2 GB	view
4k	911.1	20.7	26.6 GB	view
8k	860.4	20.1	27.3 GB	current
16k	757.2	18.9	28.5 GB	view
32k	669.3	17.1	31.0 GB	view
64k	560.2	14.4	36.1 GB	view