← Back to community benchmarks

Qwen3-VL-30B-A3B-Instruct

M4 (10c) · 32 GB · 4bit · 2026-03-11

Performance

1k

tokens

420.4

PP tok/s

44.5

TG tok/s

2436

TTFT (ms)

17.5

Peak mem (GB)

Hardware

Chip M4 (10c)

Memory 32 GB

GPU Cores 10

Software

oMLX v0.2.6

macOS macOS 26.3.1

Context 1,024

Batching Results

Batch Size	TG tok/s	Speedup
1×	44.5	1.00×
2×	58.2	1.31×
4×	62.0	1.39×