Can I run Qwen3-235B-A22B-Instruct-2507-FP8 on an NVIDIA B300?

Yes, just

Its published weights (236 GB) fit in the 259 GB an NVIDIA B300 can use, with room for ≈ 116K tokens of context.

Full analysis of Qwen3-235B-A22B-Instruct-2507-FP8 Everything that runs on NVIDIA B300 Get the weights on Hugging Face

hf download Qwen/Qwen3-235B-A22B-Instruct-2507-FP8

Files and context on NVIDIA B300

Each file of Qwen3-235B-A22B-Instruct-2507-FP8 (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	236 GB	Tight	116K	231K
4-bit (estimate)	132 GB	Fits	256K	256K

Qwen3-235B-A22B-Instruct-2507-FP8 on other hardware

NVIDIA B300Yes, just
NVIDIA H100No
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 GBNo

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.