AxionML/Nemotron-3-Super-120B-A12B-NVFP4

Quantization vs nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16. AxionML/Nemotron-3-Super-120B-A12B-NVFP4 is a quantized version of the other (U8/BF16).

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

On the Hub · Downloads on Model Pulse