← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M5 (10c) · 32 GB · 4bit · 2026-05-16

Performance

8k

tokens

182.7

PP tok/s

12.0

TG tok/s

44843

TTFT (ms)

19.1

Peak mem (GB)

Hardware

Chip M5 (10c)

Memory 32 GB

GPU Cores 10

Software

oMLX v0.3.9.dev2

macOS macOS 26.5

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	194.1	13.7	16.6 GB	view
4k	200.7	13.8	18.1 GB	view
8k	182.7	12.0	19.1 GB	current
16k	166.4	10.6	20.6 GB	view