Can I run QwQ-32B-Preview on an NVIDIA B300?

Yes

Its published weights (65.5 GB) fit in the 259 GB an NVIDIA B300 can use, with room for ≈ 32K tokens of context.

Full analysis of QwQ-32B-Preview Everything that runs on NVIDIA B300 Get the weights on Hugging Face

hf download Qwen/QwQ-32B-Preview

Files and context on NVIDIA B300

Each file of QwQ-32B-Preview (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 B300	Context (16-bit)	Context (8-bit)
As published	65.5 GB	Fits	32K	32K
4-bit (estimate)	18.4 GB	Fits	32K	32K

QwQ-32B-Preview on other hardware

NVIDIA B300Yes
NVIDIA H100Yes, just
RTX 5090Probably, at 4-bit
RTX 4090Probably, at 4-bit
RTX 3090Probably, at 4-bit
RTX 5060 Ti 16 GBNo
RTX 3060 12 GBNo
RTX 4060No
Mac with 32 GBProbably, at 4-bit
Mac with 64 GBProbably, at 4-bit
Mac with 128 GBYes

Popular models that run on NVIDIA B300

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.