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

Can I run Qwen3-VL-8B-Instruct-FP8 on an RTX 5090?

Yes

Its published weights (10.6 GB) fit in the 28.8 GB an RTX 5090 can use, with room for ≈ 121K tokens of context.

Full analysis of Qwen3-VL-8B-Instruct-FP8 Everything that runs on RTX 5090 Get the weights on Hugging Face
hf download Qwen/Qwen3-VL-8B-Instruct-FP8

Files and context on RTX 5090

Each file of Qwen3-VL-8B-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 5090 Context (16-bit)Context (8-bit)
As published10.6 GBFits121K241K
4-bit (estimate)4.93 GBFits158K256K

Qwen3-VL-8B-Instruct-FP8 on other hardware

Popular models that run on RTX 5090

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.