← Back to community benchmarks

Qwen3.6-27B-oQ6-mtp

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

Performance

32k

tokens

588.3

PP tok/s

6.4

TG tok/s

55695

TTFT (ms)

29.6

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 32,768

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	734.1	21.9	22.6 GB	view
4k	809.1	20.7	24.0 GB	view
8k	670.1	21.8	25.1 GB	view
16k	627.5	14.3	26.6 GB	view
32k	588.3	6.4	29.6 GB	current
64k	476.9	10.5	35.6 GB	view
128k	342.6	2.7	48.0 GB	view