← Back to community benchmarks

Qwen3.6-27B-oQ8-mtp

M4 Pro (20c) · 48 GB · 8bit · 2026-05-18

Performance

8k

tokens

123.4

PP tok/s

13.5

TG tok/s

66366

TTFT (ms)

31.3

Peak mem (GB)

Hardware

Chip M4 Pro (20c)

Memory 48 GB

GPU Cores 20

Software

oMLX v0.3.9.dev2

macOS macOS 15.7.3

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	120.1	14.0	28.8 GB	view
4k	124.5	14.4	30.3 GB	view
8k	123.4	13.5	31.3 GB	current
16k	120.0	12.9	32.8 GB	view