Can I run Qwen3-32B on an RTX 5090?

Yes, with a GGUF version

The published weights are too big, but the Q6_K file from Qwen/Qwen3-32B-GGUF (26.9 GB) fits, with room for ≈ 7K tokens of context.

Full analysis of Qwen3-32B Everything that runs on RTX 5090 Get the Q6_K file on Hugging Face

ollama run hf.co/Qwen/Qwen3-32B-GGUF:Q6_K

Files and context on RTX 5090

Each file of Qwen3-32B (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 5090	Context (16-bit)	Context (8-bit)
As published	65.5 GB	Doesn't fit	—	—
Q8_0Qwen/Qwen3-32B-GGUF	34.8 GB	Doesn't fit	—	—
Q6_KQwen/Qwen3-32B-GGUF	26.9 GB	Tight	7K	14K
Q5_K_MQwen/Qwen3-32B-GGUF	23.2 GB	Tight	21K	40K
Q5_0Qwen/Qwen3-32B-GGUF	22.6 GB	Fits	23K	40K
Q4_K_MQwen/Qwen3-32B-GGUF	19.8 GB	Fits	34K	40K

Qwen3-32B on other hardware

Popular models that run on RTX 5090

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.