← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M4 Max (40c) · 64 GB · 4bit · 2026-06-04

Performance

4k

tokens

245.0

PP tok/s

37.9

TG tok/s

16720

TTFT (ms)

18.0

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.4.1

macOS macOS 26.4.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
4k	245.0	37.9	18.0 GB	current
8k	247.0	36.9	19.2 GB	view
16k	240.8	35.6	20.7 GB	view