← Back to community benchmarks

Qwen3.6-27B-oQ8-mtp

M5 Max (40c) · 128 GB · 8bit · 2026-06-15

Performance

1k

tokens

721.8

PP tok/s

18.7

TG tok/s

1419

TTFT (ms)

28.3

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.4.4rc1

macOS macOS 26.5.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	721.8	18.7	28.3 GB	current
4k	861.3	18.5	29.8 GB	view
8k	826.1	18.2	30.8 GB	view
16k	718.6	17.6	32.3 GB	view