← Back to community benchmarks

Qwen3.6-27B

M4 Pro (20c) · 48 GB · 4bit · 2026-04-25

Performance

16k

tokens

120.2

PP tok/s

12.8

TG tok/s

136281

TTFT (ms)

19.1

Peak mem (GB)

Hardware

Chip M4 Pro (20c)

Memory 48 GB

GPU Cores 20

Software

oMLX v0.3.7

macOS macOS 26.4.1

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	86.8	14.4	15.8 GB	view
4k	123.5	14.7	17.3 GB	view
8k	123.6	14.1	17.9 GB	view
16k	120.2	12.8	19.1 GB	current
32k	113.3	10.8	21.6 GB	view
64k	100.4	6.5	26.7 GB	view
128k	80.0	3.9	37.0 GB	view