← Back to community benchmarks

Qwen3.6-27B-oQ8-mtp

M5 Max (40c) · 128 GB · 8bit · 2026-05-19

Performance

16k

tokens

750.3

PP tok/s

27.1

TG tok/s

21835

TTFT (ms)

33.2

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.9.dev2

macOS macOS 26.5

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	720.0	29.9	29.3 GB	view
4k	827.7	29.0	30.7 GB	view
8k	790.5	28.6	31.7 GB	view
16k	750.3	27.1	33.2 GB	current
32k	701.1	25.3	36.2 GB	view