← Back to community benchmarks

Qwen3.6-27B

M5 Max (40c) · 128 GB · 4bit · 2026-05-01

Performance

32k

tokens

708.9

PP tok/s

27.6

TG tok/s

46226

TTFT (ms)

20.9

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.8rc1

macOS macOS 26.4.1

Context 32,768

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	808.2	35.2	15.1 GB	view
4k	920.3	34.3	16.5 GB	view
8k	864.5	33.1	17.1 GB	view
16k	783.9	30.5	18.4 GB	view
32k	708.9	27.6	20.9 GB	current