← Back to community benchmarks

Qwen3.6-27B-oQ8-mtp

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

Performance

1k

tokens

62.4

PP tok/s

13.5

TG tok/s

16404

TTFT (ms)

28.8

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 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	62.4	13.5	28.8 GB	current
4k	63.5	12.8	30.3 GB	view
8k	63.9	12.7	31.3 GB	view
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