§01·model · /models

Qwen3 30B-A3B

llmactiveApache-2.0

30B Mixture-of-Experts LLM by Alibaba (Qwen3-30B-A3B, ~3B active per token) with hybrid thinking modes. Apache-2.0.

Download· 4 variants

§02·GPUs that run this model

4 total

GPU	VRAM	Series	Best speed	Min VRAM	Works	Benchmarks	Recipe
RTX 5090	32GB	50	226.1tokens/s		✓	2	recipe	check ↗
RTX 3090 Ti	24GB	30	166.9tokens/s	24GB	✓	2	recipe	check ↗
RTX 3090	24GB	30	153.6tokens/s	24GB	✓	2	recipe	check ↗
RTX 4070	12GB	40			~	0	recipe	check ↗

✓ benchmarked·~ runs via recipe (not benchmarked)·— untested·✕doesn't fit