← Back to community benchmarks

Qwen3.5-9B

M4 Pro (16c) · 64 GB · 8bit · 2026-03-10

Performance

8k

tokens

356.6

PP tok/s

26.6

TG tok/s

22974

TTFT (ms)

11.2

Peak mem (GB)

Hardware

Chip M4 Pro (16c)

Memory 64 GB

GPU Cores 16

Software

oMLX v0.2.6

macOS macOS 26.3

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
4k	361.9	27.4	11.0 GB	view
8k	356.6	26.6	11.2 GB	current
16k	343.7	25.0	11.7 GB	view
32k	324.0	22.3	12.7 GB	view