← Back to community benchmarks

Qwen3.5-9B

M4 (10c) · 32 GB · 8bit · 2026-04-25

Performance

1k

tokens

179.0

PP tok/s

77.5

TG tok/s

5721

TTFT (ms)

12.2

Peak mem (GB)

Hardware

Chip M4 (10c)

Memory 32 GB

GPU Cores 10

Software

oMLX v0.3.6

macOS macOS 26.3.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	179.0	77.5	12.2 GB	current
4k	177.7	11.6	11.4 GB	view
8k	220.2	11.3	11.8 GB	view
16k	483.6	9.4	12.5 GB	view
32k	457.9	9.3	13.2 GB	view