← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M4 Pro (20c) · 48 GB · 4bit · 2026-05-22

Performance

64k

tokens

98.2

PP tok/s

14.1

TG tok/s

667328

TTFT (ms)

27.6

Peak mem (GB)

Hardware

Chip M4 Pro (20c)

Memory 48 GB

GPU Cores 20

Software

oMLX v0.3.9.dev2

macOS macOS 26.5

Context 65,536

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	120.8	22.4	16.7 GB	view
4k	119.9	19.3	18.2 GB	view
64k	98.2	14.1	27.6 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	22.4	1.00×
2×	26.5	1.18×
4×	29.0	1.29×