← Back to community benchmarks

Qwen3.6-27B-oQ4

M4 Max (40c) · 64 GB · 4bit · 2026-05-05

Performance

1k

tokens

221.0

PP tok/s

85.5

TG tok/s

4634

TTFT (ms)

17.8

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.3.8

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	221.0	85.5	17.8 GB	current
4k	183.4	23.2	17.9 GB	view
8k	184.6	22.3	18.9 GB	view
16k	138.3	10.2	20.4 GB	view