← Back to community benchmarks

Qwen3.6-27B-oQ6-mtp

M5 Max (40c) · 64 GB · 6bit · 2026-05-22

Performance

1k

tokens

732.0

PP tok/s

32.7

TG tok/s

1399

TTFT (ms)

23.0

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.3.9

macOS macOS 26.5

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	732.0	32.7	23.0 GB	current
4k	732.8	31.2	24.4 GB	view
8k	674.6	28.2	25.4 GB	view