← Back to community benchmarks

Qwen3.6-27B-mtp

M4 Max (40c) · 128 GB · 8bit · 2026-05-07

Performance

8k

tokens

242.8

PP tok/s

25.4

TG tok/s

33742

TTFT (ms)

31.3

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.9.dev1

macOS macOS 26.4.1

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	233.7	26.4	28.8 GB	view
4k	244.5	26.2	30.3 GB	view
8k	242.8	25.4	31.3 GB	current
16k	235.5	23.6	32.8 GB	view
32k	224.9	22.6	35.8 GB	view
64k	198.0	19.0	41.8 GB	view