← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M5 (10c) · 32 GB · 4bit · 2026-05-17

Performance

8k

tokens

184.7

PP tok/s

7.3

TG tok/s

44346

TTFT (ms)

18.8

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	191.1	7.2	16.4 GB	view
4k	198.7	7.4	17.8 GB	view
8k	184.7	7.3	18.8 GB	current