← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

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

Performance

4k

tokens

468.3

PP tok/s

25.7

TG tok/s

8746

TTFT (ms)

18.2

Peak mem (GB)

Hardware

Chip M5 Pro (20c)

Memory 64 GB

GPU Cores 20

Software

oMLX v0.3.9

macOS macOS 26.4.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	429.9	26.3	16.7 GB	view
4k	468.3	25.7	18.2 GB	current
8k	459.4	24.7	19.2 GB	view
16k	426.4	23.2	20.7 GB	view
32k	382.9	21.6	23.7 GB	view