← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

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

Performance

16k

tokens

116.9

PP tok/s

20.1

TG tok/s

140140

TTFT (ms)

20.7

Peak mem (GB)

Hardware

Chip M4 Pro (20c)

Memory 64 GB

GPU Cores 20

Software

oMLX v0.3.9

macOS macOS 26.5

Context 16,384

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	view
8k	117.9	20.8	19.2 GB	view
16k	116.9	20.1	20.7 GB	current
32k	110.7	17.7	23.7 GB	view