AxionML/Nemotron-3-Ultra-550B-A55B-NVFP4

Quantization vs nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16. AxionML/Nemotron-3-Ultra-550B-A55B-NVFP4 is a quantized version of the other (U8/F8_E4M3).

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

On the Hub · Downloads on Model Pulse