← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

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

Performance

16k

tokens

240.8

PP tok/s

35.6

TG tok/s

68041

TTFT (ms)

20.7

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 16,384

Performance by Context Length

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