← Back to community benchmarks

Qwen3.5-9B

M4 (10c) · 16 GB · 4bit · 2026-03-11

Performance

8k

tokens

221.3

PP tok/s

20.1

TG tok/s

37024

TTFT (ms)

7.0

Peak mem (GB)

Hardware

Chip M4 (10c)

Memory 16 GB

GPU Cores 10

Software

oMLX v0.2.8

macOS macOS 26.3

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
8k	221.3	20.1	7.0 GB	current
16k	204.3	18.2	7.5 GB	view