← Back to community benchmarks

Qwen3.6-27B-UD

M3 Max (40c) · 64 GB · 4bit · 2026-05-04

Performance

1k

tokens

151.3

PP tok/s

10.6

TG tok/s

6767

TTFT (ms)

25.2

Peak mem (GB)

Hardware

Chip M3 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.3.7

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	151.3	10.6	25.2 GB	current
4k	153.5	10.3	26.6 GB	view
8k	157.2	9.5	27.3 GB	view