← Back to community benchmarks

Qwen3.6-27B

M4 Max (40c) · 64 GB · 4bit · 2026-04-25

Performance

32k

tokens

693.8

PP tok/s

19.1

TG tok/s

47228

TTFT (ms)

21.6

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.3.8.dev1

macOS macOS 26.4.1

Context 32,768

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	241.8	29.0	16.6 GB	view
4k	209.6	25.1	18.0 GB	view
32k	693.8	19.1	21.6 GB	current