Some straight nvfp4 conversions of the WAN 2.2 models done with https://github.com/gitmylo/ModelConverter.

You will need a NVidia 5000 Series GPU, Pytorch compiled with CUDA 13 support and a current Nvidia driver installed to gain any speed advantage from this.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support