← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M4 Pro (20c) · 64 GB · 4bit · 2026-05-22

Performance

4k

tokens

120.9

PP tok/s

21.5

TG tok/s

33888

TTFT (ms)

18.2

Peak mem (GB)

Hardware

Chip M4 Pro (20c)

Memory 64 GB

GPU Cores 20

Software

oMLX v0.3.9

macOS macOS 26.5

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	124.1	22.7	16.7 GB	view
4k	120.9	21.5	18.2 GB	current
8k	117.9	20.8	19.2 GB	view
16k	116.9	20.1	20.7 GB	view
32k	110.7	17.7	23.7 GB	view