← Back to community benchmarks

Qwen3.6-27B-oQ6-mtp

M5 Max (40c) · 64 GB · 6bit · 2026-05-15

Performance

16k

tokens

585.7

PP tok/s

28.4

TG tok/s

27974

TTFT (ms)

26.9

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 64 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	740.5	32.9	23.0 GB	view
4k	705.3	30.7	24.4 GB	view
8k	646.3	28.1	25.4 GB	view
16k	585.7	28.4	26.9 GB	current