← Back to community benchmarks

Qwen3.6-27B-OptiQ

M5 Max (40c) · 128 GB · 4bit · 2026-06-19

Performance

64k

tokens

538.0

PP tok/s

21.2

TG tok/s

121823

TTFT (ms)

32.2

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.4.4rc1

macOS macOS

Context 65,536

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
32k	723.7	25.0	25.0 GB	view
64k	538.0	21.2	32.2 GB	current
128k	339.5	15.5	44.6 GB	view