← Back to community benchmarks

Qwen3.5-9B

M4 Pro (16c) · 24 GB · 4bit · 2026-03-11

Performance

1k

tokens

305.2

PP tok/s

35.0

TG tok/s

3355

TTFT (ms)

7.8

Peak mem (GB)

Hardware

Chip M4 Pro (16c)

Memory 24 GB

GPU Cores 16

Software

oMLX v0.2.6

macOS macOS 26.3.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	305.2	35.0	7.8 GB	current
4k	321.0	33.0	8.2 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	35.0	1.00×
2×	60.0	1.71×
4×	70.9	2.03×