FP8 quantized version of AuraFlow v0.3

Just casted to torch.float8_e4m3fn all linear weights of the flow transformer except t_embedder, final_linear, modF.

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

Model tree for p1atdev/AuraFlow-v0.3-fp8

Base model

Quantized

(4)

this model