← Back to community benchmarks

Qwen3.6-27B-OptiQ

M5 Max (40c) · 64 GB · 4bit · 2026-07-24

Performance

32k

tokens

575.9

PP tok/s

23.5

TG tok/s

56899

TTFT (ms)

26.2

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.5.3

macOS macOS 26.4

Context 32,768

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
16k	695.7	21.7	22.5 GB	view
32k	575.9	23.5	26.2 GB	current
64k	481.4	17.6	32.2 GB	view