← Back to community benchmarks

Qwen3.5-9Bvlm

M4 Pro (16c) · 24 GB · 4bit · 2026-04-28

Performance

4k

tokens

354.2

PP tok/s

50.5

TG tok/s

11563

TTFT (ms)

6.2

Peak mem (GB)

Hardware

Chip M4 Pro (16c)

Memory 24 GB

GPU Cores 16

Software

oMLX v0.3.8rc1

macOS macOS 26.2

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	342.0	52.2	5.6 GB	view
4k	354.2	50.5	6.2 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	52.2	1.00×
2×	86.1	1.65×
4×	92.8	1.78×