grumd0/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4-GGUF
Not comparable yet vs nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (442 of 165860/925 match), usually an architecture llama.cpp's name map doesn't cover yet.