nvidia/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-BF16
Different architecture vs nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16. Different architecture: only 8763 of 42683/42683 tensors match by name and shape.
5 derivatives checked
- RemySkye/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-GGUF: Not comparable yet
- Myric/Nemotron-Labs-3-Puzzle-75B-A9B-APEX-GGUF: Not comparable yet
- MRockatansky/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-MTP-GGUF: Not comparable yet
- danielrmay/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-W4A16: Quantization
- georgeis55/Nemotron-Labs-3-Puzzle-75B-A9B-MLX-6bit: Quantization