← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M5 Pro (20c) · 48 GB · 4bit · 2026-05-09

Performance

16k

tokens

371.5

PP tok/s

22.5

TG tok/s

44098

TTFT (ms)

20.7

Peak mem (GB)

Hardware

Chip M5 Pro (20c)

Memory 48 GB

GPU Cores 20

Software

oMLX v0.3.9.dev1

macOS macOS 26.5

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	424.5	26.1	16.8 GB	view
4k	453.0	25.0	18.2 GB	view
8k	385.6	23.3	19.2 GB	view
16k	371.5	22.5	20.7 GB	current
32k	334.9	19.2	23.7 GB	view
64k	263.5	13.8	29.8 GB	view