← Back to community benchmarks

Qwen3.6-27B-oQ6-fp16-mtp

M3 Max (40c) · 64 GB · 6bit · 2026-05-23

Performance

8k

tokens

213.6

PP tok/s

15.5

TG tok/s

38357

TTFT (ms)

25.1

Peak mem (GB)

Hardware

Chip M3 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.3.9

macOS macOS 26.4.1

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	209.3	16.0	22.6 GB	view
4k	220.4	15.8	24.0 GB	view
8k	213.6	15.5	25.1 GB	current