← Back to community benchmarks

Qwen3.5-9B

M3 Pro (14c) · 18 GB · 4bit · 2026-03-10

Performance

1k

tokens

259.2

PP tok/s

27.9

TG tok/s

3951

TTFT (ms)

5.8

Peak mem (GB)

Hardware

Chip M3 Pro (14c)

Memory 18 GB

GPU Cores 14

Software

oMLX v0.2.6

macOS macOS 15.3.2

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	259.2	27.9	5.8 GB	current
4k	270.4	27.2	6.0 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	27.9	1.00×
2×	55.1	1.97×
4×	65.1	2.33×