← Back to community benchmarks

Qwen3.6-27B

M3 Max (30c) · 36 GB · 4bit · 2026-04-26

Performance

8k

tokens

143.6

PP tok/s

16.2

TG tok/s

57057

TTFT (ms)

17.9

Peak mem (GB)

Hardware

Chip M3 Max (30c)

Memory 36 GB

GPU Cores 30

Software

oMLX v0.3.6

macOS macOS 26.4.1

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
8k	143.6	16.2	17.9 GB	current
16k	154.0	14.4	19.1 GB	view