Model Anatomy See what's inside open-weight AI models

Can I run Qwen3-VL-32B-Instruct-FP8 on an RTX PRO 6000 Blackwell?

Yes

Its published weights (35.5 GB) fit in the 86.4 GB an RTX PRO 6000 Blackwell can use, with room for ≈ 190K tokens of context.

Full analysis of Qwen3-VL-32B-Instruct-FP8 Everything that runs on RTX PRO 6000 Blackwell Get the weights on Hugging Face
hf download Qwen/Qwen3-VL-32B-Instruct-FP8

Files and context on RTX PRO 6000 Blackwell

Each file of Qwen3-VL-32B-Instruct-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.

FileSizeOn RTX PRO 6000 Blackwell Context (16-bit)Context (8-bit)
As published35.5 GBFits190K256K
4-bit (estimate)18.8 GBFits252K256K

Qwen3-VL-32B-Instruct-FP8 on other hardware

Popular models that run on RTX PRO 6000 Blackwell

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.