nvfp4 ?
#25
by
lanranjun - opened
Have you ever used the LTX-2.3 NVFP4 version large model? How effective is it?
ltx-2.4 nvfp4 + gemma 12b fp4
Havent used the NVFP4 myself, since my GPU is a bit too old to benefit from that.
But if you have RTX 4xxx or 5xxx it can run well with a much smaller file size.
And Kijai made some input_scaled modes as well that also are for newer graphic cards (Blackwell, RTX 4xxx, 5xxx etc), that can run a lot faster.
https://huggingface.co/Kijai/LTX2.3_comfy/tree/main/diffusion_models
They all do the same thing, so its more about size, and speed.
And if you have the GPU for it worth trying out, specially the input_scaled i saw had some good feedback