← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

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

Performance

8k

tokens

385.4

PP tok/s

16.2

TG tok/s

21254

TTFT (ms)

18.5

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 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	360.2	16.8	16.5 GB	view
8k	385.4	16.2	18.5 GB	current
64k	273.9	2.7	27.3 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	16.8	1.00×
2×	25.4	1.51×
4×	28.5	1.70×