← Back to community benchmarks

Qwen3-VL-30B-A3B-Instruct

M4 Pro (16c) · 64 GB · 4bit · 2026-03-16

Performance

1k

tokens

667.2

PP tok/s

68.6

TG tok/s

1535

TTFT (ms)

17.6

Peak mem (GB)

Hardware

Chip M4 Pro (16c)

Memory 64 GB

GPU Cores 16

Software

oMLX v0.2.13

macOS macOS 15.7.3

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	667.2	68.6	17.6 GB	current
4k	642.2	57.4	18.1 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	68.6	1.00×
2×	95.6	1.39×
4×	109.0	1.59×