← Back to community benchmarks

Qwen3.5-9B

M4 Pro (16c) · 64 GB · 4bit · 2026-03-10

Performance

32k

tokens

324.0

PP tok/s

35.3

TG tok/s

101147

TTFT (ms)

8.7

Peak mem (GB)

Hardware

Chip M4 Pro (16c)

Memory 64 GB

GPU Cores 16

Software

oMLX v0.2.6

macOS macOS 26.3

Context 32,768

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
8k	358.3	45.2	7.1 GB	view
16k	345.4	29.8	7.6 GB	view
32k	324.0	35.3	8.7 GB	current
64k	287.0	23.8	10.8 GB	view