← Back to community benchmarks

Qwen3.6-27B

M4 (10c) · 32 GB · 4bit · 2026-04-26

Performance

16k

tokens

60.4

PP tok/s

5.9

TG tok/s

271459

TTFT (ms)

19.1

Peak mem (GB)

Hardware

Chip M4 (10c)

Memory 32 GB

GPU Cores 10

Software

oMLX v0.3.7

macOS macOS 26.4.1

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	62.7	6.7	15.8 GB	view
4k	63.1	6.6	17.2 GB	view
8k	62.3	6.3	17.8 GB	view
16k	60.4	5.9	19.1 GB	current