← Back to community benchmarks

Qwen3.6-27B-oQ8-mtp

M4 Max (40c) · 128 GB · 8bit · 2026-05-16

Performance

4k

tokens

158.4

PP tok/s

16.6

TG tok/s

25854

TTFT (ms)

30.3

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.9.dev2

macOS macOS 15.7

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	142.4	16.0	28.8 GB	view
4k	158.4	16.6	30.3 GB	current
8k	156.8	15.5	31.3 GB	view