← Back to community benchmarks

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

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

Performance

16k

tokens

632.0

PP tok/s

19.3

TG tok/s

25924

TTFT (ms)

26.6

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 16,384

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	view
8k	642.6	21.9	24.6 GB	view
16k	632.0	19.3	26.6 GB	current
32k	557.4	15.4	29.6 GB	view
64k	456.9	8.4	35.6 GB	view