← Back to community benchmarks

Qwen3.6-27B-MTPLX-Optimized-Speed

M5 Max (40c) · 128 GB · 4bit · 2026-05-09

Performance

16k

tokens

744.2

PP tok/s

29.9

TG tok/s

22017

TTFT (ms)

21.9

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.9.dev1

macOS macOS 26.4.1

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	794.0	33.0	18.0 GB	view
4k	920.5	32.3	19.4 GB	view
8k	845.0	31.3	20.4 GB	view
16k	744.2	29.9	21.9 GB	current
32k	666.4	28.4	24.9 GB	view
64k	550.4	23.5	31.0 GB	view
128k	402.8	19.1	43.4 GB	view