← Back to community benchmarks

Qwen3.6-27B-oQ8-mtp

M4 Max (40c) · 128 GB · 8bit · 2026-05-19

Performance

8k

tokens

154.2

PP tok/s

16.0

TG tok/s

53139

TTFT (ms)

31.3

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.9rc1

macOS macOS 15.7

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	235.1	16.8	28.8 GB	view
4k	150.6	16.1	30.3 GB	view
8k	154.2	16.0	31.3 GB	current