RedHatAI/NVIDIA-Nemotron-3-Ultra-550B-A55B-FP8-block

Quantization vs nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16. RedHatAI/NVIDIA-Nemotron-3-Ultra-550B-A55B-FP8-block is a quantized version of the other (F8_E4M3/BF16).

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse