← Back to community benchmarks

Qwen3.6-27B-oQ8-mtp

M1 Max (24c) · 64 GB · 8bit · 2026-05-18

Performance

8k

tokens

63.9

PP tok/s

12.7

TG tok/s

128120

TTFT (ms)

31.3

Peak mem (GB)

Hardware

Chip M1 Max (24c)

Memory 64 GB

GPU Cores 24

Software

oMLX v0.3.9.dev2

macOS macOS 26.5

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	62.4	13.5	28.8 GB	view
4k	63.5	12.8	30.3 GB	view
8k	63.9	12.7	31.3 GB	current
16k	62.8	11.8	32.8 GB	view
32k	60.5	10.5	35.8 GB	view
64k	55.3	8.4	41.8 GB	view