← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M5 Pro (20c) · 64 GB · 4bit · 2026-05-21

Performance

8k

tokens

467.8

PP tok/s

25.1

TG tok/s

17512

TTFT (ms)

19.2

Peak mem (GB)

Hardware

Chip M5 Pro (20c)

Memory 64 GB

GPU Cores 20

Software

oMLX v0.3.9rc1

macOS macOS 26.4.1

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	430.5	26.1	16.7 GB	view
4k	469.2	25.8	18.2 GB	view
8k	467.8	25.1	19.2 GB	current
16k	438.0	24.0	20.7 GB	view
32k	395.8	21.5	23.7 GB	view