← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M5 Pro (16c) · 48 GB · 4bit · 2026-05-12

Performance

64k

tokens

280.4

PP tok/s

8.8

TG tok/s

233723

TTFT (ms)

27.9

Peak mem (GB)

Hardware

Chip M5 Pro (16c)

Memory 48 GB

GPU Cores 16

Software

oMLX v0.3.8

macOS macOS 26.4.1

Context 65,536

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	361.0	17.4	16.5 GB	view
64k	280.4	8.8	27.9 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	17.4	1.00×
2×	23.3	1.34×
4×	27.1	1.56×