Can I run Qwen3-VL-30B-A3B-Instruct on an RTX 3090?

Yes, with a GGUF version

The published weights are too big, but the Q4_K_M file from Qwen/Qwen3-VL-30B-A3B-Instruct-GGUF (18.6 GB) fits, with room for ≈ 30K tokens of context.

Full analysis of Qwen3-VL-30B-A3B-Instruct Everything that runs on RTX 3090 Get the Q4_K_M file on Hugging Face

ollama run hf.co/Qwen/Qwen3-VL-30B-A3B-Instruct-GGUF:Q4_K_M

Files and context on RTX 3090

Each file of Qwen3-VL-30B-A3B-Instruct (and of GGUF versions the site has analyzed), and how much context fits next to it, with the context cache in 16-bit or 8-bit.

File	Size	On RTX 3090	Context (16-bit)	Context (8-bit)
As published	62.1 GB	Doesn't fit	—	—
F16Qwen/Qwen3-VL-30B-A3B-Instruct-GGUF	61.1 GB	Doesn't fit	—	—
Q8_0Qwen/Qwen3-VL-30B-A3B-Instruct-GGUF	32.5 GB	Doesn't fit	—	—
Q4_K_MQwen/Qwen3-VL-30B-A3B-Instruct-GGUF	18.6 GB	Tight	30K	60K

Qwen3-VL-30B-A3B-Instruct on other hardware

Popular models that run on RTX 3090

Assumes 90% of the card's memory is usable and at least 4K tokens of context for one conversation, with the context cache in 16-bit unless noted. Fits leaves at least 20% of that memory for context; Tight leaves less.