nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
14 derivatives checked
- RedHatAI/NVIDIA-Nemotron-3-Ultra-550B-A55B-quantized.w4a16: Quantization
- unsloth/NVIDIA-Nemotron-3-Ultra-550B-A55B-GGUF: Same weights, converted
- nvidia/Nemotron-3-Labs-Ultra-Math-SFT: Full fine-tune
- RedHatAI/NVIDIA-Nemotron-3-Ultra-550B-A55B-FP8-block: Quantization
- nvidia/Nemotron-3-Labs-Ultra-Math-RL: Full fine-tune
- DevQuasar/nvidia.NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16-GGUF: Quantization
- RedHatAI/NVIDIA-Nemotron-3-Ultra-550B-A55B-FP8-dynamic: Quantization
- Laerins/OpenYourMind-NVIDIA-Nemotron-3-Ultra-550B-A55B-abliterated-uncensored: Partial fine-tune
- hell0ks/NVIDIA-Nemotron-3-Ultra-550B-A55B-GGUF: Not comparable yet
- AesSedai/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16-GGUF: Quantization
- mlx-community/Nemotron-3-Ultra-550B-A55B-4bit: Quantization
- AxionML/Nemotron-3-Ultra-550B-A55B-NVFP4: Quantization
- OpenYourMind/OpenYourMind-NVIDIA-Nemotron-3-Ultra-550B-A55B-abliterated-uncensored-NVFP4: Quantization
- OpenYourMind/OpenYourMind-NVIDIA-Nemotron-3-Ultra-550B-A55B-abliterated-uncensored: Partial fine-tune
12 other repos hold byte-for-byte identical weight files.