← Back to community benchmarks

Qwen3.6-27B-UD

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

Performance

32k

tokens

669.3

PP tok/s

17.1

TG tok/s

48957

TTFT (ms)

31.0

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.6

macOS macOS 26.4

Context 32,768

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	view
16k	757.2	18.9	28.5 GB	view
32k	669.3	17.1	31.0 GB	current
64k	560.2	14.4	36.1 GB	view