nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-Base-BF16
2 derivatives checked
- inference-optimization/NemotronH-0.3B-A0.3B: Different architecture
- avar6/NVIDIA-Nemotron-3-Ultra-550B-A55B-Base-gguf: Quantization
2 other repos hold byte-for-byte identical weight files.