nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4
Quantization vs nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16. nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4 is a quantized version of the other (U8/BF16).
3 derivatives checked
- unsloth/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4: Identical copy
- mlx-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4: Different architecture
- FedericoFB/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4-GGUF: Not comparable yet
6 other repos hold byte-for-byte identical weight files.