FedericoFB/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-NVFP4-GGUF
Not comparable yet vs nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-NVFP4. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (217 of 25205/493 match), usually an architecture llama.cpp's name map doesn't cover yet.