← Back to community benchmarks

Qwen3.6-27B-oQ6-fp16-mtp

M5 Max (40c) · 128 GB · 6bit · 2026-05-21

Performance

4k

tokens

600.8

PP tok/s

20.7

TG tok/s

6818

TTFT (ms)

24.0

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.8

macOS macOS 26.4.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	487.5	22.9	22.6 GB	view
4k	600.8	20.7	24.0 GB	current
8k	642.6	21.9	24.6 GB	view
16k	632.0	19.3	26.6 GB	view
32k	557.4	15.4	29.6 GB	view
64k	456.9	8.4	35.6 GB	view