← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M3 Max (40c) · 64 GB · 4bit · 2026-06-05

Performance

16k

tokens

195.4

PP tok/s

26.9

TG tok/s

83848

TTFT (ms)

20.1

Peak mem (GB)

Hardware

Chip M3 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.4.1

macOS macOS 15.7.7

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
16k	195.4	26.9	20.1 GB	current
32k	152.3	14.9	23.7 GB	view
64k	126.4	13.0	29.8 GB	view