← Back to community benchmarks

Qwen3.5-9B

M4 Pro (16c) · 64 GB · 4bit · 2026-03-13

Performance

32k

tokens

230.0

PP tok/s

26.9

TG tok/s

142484

TTFT (ms)

8.7

Peak mem (GB)

Hardware

Chip M4 Pro (16c)

Memory 64 GB

GPU Cores 16

Software

oMLX v0.2.10

macOS macOS 26.1

Context 32,768

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	193.9	23.9	6.7 GB	view
4k	305.1	44.1	7.0 GB	view
8k	306.7	43.4	7.1 GB	view
16k	275.7	28.1	7.6 GB	view
32k	230.0	26.9	8.7 GB	current