Can I run Qwen-72B on an NVIDIA B200?

Yes, just

Its published weights (145 GB) fit in the 162 GB an NVIDIA B200 can use, with room for ≈ 6K tokens of context.

Full analysis of Qwen-72B Everything that runs on NVIDIA B200 Get the weights on Hugging Face

hf download Qwen/Qwen-72B

Files and context on NVIDIA B200

Each file of Qwen-72B (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	145 GB	Tight	6K	13K
4-bit (estimate)	40.7 GB	Fits	32K	32K

Qwen-72B on other hardware

NVIDIA B200Yes, just
NVIDIA H100Probably, at 4-bit
RTX 5090No
RTX 4090No
RTX 3090No
RTX 5060 Ti 16 GBNo
RTX 3060 12 GBNo
RTX 4060No
Mac with 32 GBNo
Mac with 64 GBNo
Mac with 128 GBProbably, at 4-bit

Popular models that run on NVIDIA B200

Qwen3-0.6BQwen · 752M
Qwen3-VL-8B-InstructQwen · 8.77B
gpt2openai-community · 137M
Qwen3-8BQwen · 8.19B
Qwen3-Coder-30B-A3B-Instruct-GGUFunsloth · 30.5B
gemma-4-26B-A4B-itgoogle · 25.8B
Qwen2.5-7B-InstructQwen · 7.62B
Qwen3.5-9BQwen · 9.65B

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.