I don't think consumer GPUs can render this in real-time yet. I've seen around 5 to 10fps framerates on a 3080 just rendering monoscopic output (from memory)

not NERFs but there was a google experiment with volumetric / layered videos which I found super fun - https://augmentedperception.github.io/deepviewvideo/

the decoding doesnt use a neural function but this is actually surprisingly impressive at transmitting the feeling of being "there" try the one demo with the goat hanging out by the camera, I found it surprisingly nice