Can I run Qwen3-4B on an NVIDIA B200?

Yes

Its published weights (8.04 GB) fit in the 162 GB an NVIDIA B200 can use, with room for ≈ 40K tokens of context.

Full analysis of Qwen3-4B Everything that runs on NVIDIA B200 Get the weights on Hugging Face

hf download Qwen/Qwen3-4B

Files and context on NVIDIA B200

Each file of Qwen3-4B (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 NVIDIA B200	Context (16-bit)	Context (8-bit)
As published	8.04 GB	Fits	40K	40K
Q8_0Qwen/Qwen3-4B-GGUF	4.28 GB	Fits	40K	40K
Q6_KQwen/Qwen3-4B-GGUF	3.31 GB	Fits	40K	40K
Q5_K_MQwen/Qwen3-4B-GGUF	2.89 GB	Fits	40K	40K
Q5_0Qwen/Qwen3-4B-GGUF	2.82 GB	Fits	40K	40K
Q4_K_MQwen/Qwen3-4B-GGUF	2.50 GB	Fits	40K	40K

Qwen3-4B on other hardware

Popular models that run on NVIDIA B200

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.