← Back to community benchmarks

Qwen3.6-27B-OptiQ

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

Performance

16k

tokens

695.7

PP tok/s

21.7

TG tok/s

23549

TTFT (ms)

22.5

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.5.3

macOS macOS 26.4

Context 16,384

Performance by Context Length

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