← Back to community benchmarks

Qwen3.6-27B-oQ6-mtp

M5 Max (40c) · 128 GB · 6bit · 2026-05-22

Performance

1k

tokens

742.2

PP tok/s

34.4

TG tok/s

1380

TTFT (ms)

23.0

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.9

macOS macOS 26.5

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	742.2	34.4	23.0 GB	current
4k	815.2	34.4	24.4 GB	view
8k	778.9	31.5	25.4 GB	view
16k	719.6	29.9	26.9 GB	view
32k	655.2	29.7	29.9 GB	view
64k	512.0	20.6	36.0 GB	view
128k	359.1	16.5	48.3 GB	view
195k	263.0	13.2	63.0 GB	view