← Back to community benchmarks

Qwen3.5-27B

M4 Max (40c) · 128 GB · 4bit · 2026-03-10

Performance

32k

tokens

215.3

PP tok/s

21.4

TG tok/s

152165

TTFT (ms)

20.1

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.2.6

macOS macOS 15.7.4

Context 32,768

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
4k	248.3	27.9	17.0 GB	view
8k	228.8	26.4	17.4 GB	view
16k	230.9	24.0	18.3 GB	view
32k	215.3	21.4	20.1 GB	current
64k	177.9	16.8	23.6 GB	view