← Back to community benchmarks

Qwen3.5-9B

M4 (10c) · 16 GB · 4bit · 2026-03-11

Performance

16k

tokens

212.5

PP tok/s

17.7

TG tok/s

77107

TTFT (ms)

7.5

Peak mem (GB)

Hardware

Chip M4 (10c)

Memory 16 GB

GPU Cores 10

Software

oMLX v0.2.7

macOS macOS 15.7.4

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
8k	221.2	19.3	7.0 GB	view
16k	212.5	17.7	7.5 GB	current
32k	193.3	14.7	8.5 GB	view