← Back to community benchmarks

Qwen3.6-27B-oQ6

M4 Max (40c) · 128 GB · 6bit · 2026-04-30

Performance

16k

tokens

207.3

PP tok/s

17.3

TG tok/s

79021

TTFT (ms)

25.9

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.8rc1

macOS macOS 26.4.1

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	219.3	95.8	26.3 GB	view
4k	211.5	20.0	24.0 GB	view
8k	198.6	19.1	24.6 GB	view
16k	207.3	17.3	25.9 GB	current