Model Anatomy See what's inside open-weight AI models

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

Yes, with a GGUF version

The published weights are too big, but the Q5_0 file from Qwen/Qwen3-30B-A3B-GGUF (21.1 GB) fits, with room for ≈ 5K tokens of context.

Full analysis of Qwen3-30B-A3B Everything that runs on RTX 3090 Get the Q5_0 file on Hugging Face
ollama run hf.co/Qwen/Qwen3-30B-A3B-GGUF:Q5_0

Files and context on RTX 3090

Each file of Qwen3-30B-A3B (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.

FileSizeOn RTX 3090 Context (16-bit)Context (8-bit)
As published61.1 GBDoesn't fit——
Q8_0Qwen/Qwen3-30B-A3B-GGUF32.5 GBDoesn't fit——
Q6_KQwen/Qwen3-30B-A3B-GGUF25.1 GBDoesn't fit——
Q5_K_MQwen/Qwen3-30B-A3B-GGUF21.7 GBDoesn't fit——
Q5_0Qwen/Qwen3-30B-A3B-GGUF21.1 GBTight5K10K
Q4_K_MQwen/Qwen3-30B-A3B-GGUF18.6 GBTight30K40K

Qwen3-30B-A3B 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.