← Back to community benchmarks

Qwen3.5-27B

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

Performance

16k

tokens

230.9

PP tok/s

24.0

TG tok/s

70944

TTFT (ms)

18.3

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 16,384

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	current
32k	215.3	21.4	20.1 GB	view
64k	177.9	16.8	23.6 GB	view