← Back to community benchmarks

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

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

Performance

32k

tokens

666.4

PP tok/s

28.4

TG tok/s

49172

TTFT (ms)

24.9

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 32,768

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	view
32k	666.4	28.4	24.9 GB	current
64k	550.4	23.5	31.0 GB	view
128k	402.8	19.1	43.4 GB	view