← Back to community benchmarks

Qwen3.6-27B

M5 Max (40c) · 128 GB · 8bit · 2026-06-17

Performance

64k

tokens

458.6

PP tok/s

10.8

TG tok/s

142914

TTFT (ms)

46.2

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.4.3

macOS macOS 26.5.1

Context 65,536

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
32k	621.6	14.8	38.9 GB	view
64k	458.6	10.8	46.2 GB	current
128k	283.7	9.4	58.6 GB	view
195k	114.0	8.4	72.7 GB	view