RemySkye/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-GGUF
Not comparable yet vs nvidia/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-BF16. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (91 of 42683/781 match), usually an architecture llama.cpp's name map doesn't cover yet.