← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

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

Performance

4k

tokens

453.0

PP tok/s

25.0

TG tok/s

9043

TTFT (ms)

18.2

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 4,096

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	current
8k	385.6	23.3	19.2 GB	view
16k	371.5	22.5	20.7 GB	view
32k	334.9	19.2	23.7 GB	view
64k	263.5	13.8	29.8 GB	view