← Back to community benchmarks

Qwen3.6-27B-UD

M5 Max (40c) · 128 GB · 4bit · 2026-04-30

Performance

16k

tokens

831.5

PP tok/s

19.8

TG tok/s

19703

TTFT (ms)

28.5

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.8rc1

macOS macOS 26.4

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	792.2	21.4	25.2 GB	view
4k	930.4	21.0	26.6 GB	view
8k	855.1	19.3	27.2 GB	view
16k	831.5	19.8	28.5 GB	current