DreamFoundries/NVIDIA-Nemotron-3-Super-120B-A12B-BF16-8bit

Quantization vs nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16. DreamFoundries/NVIDIA-Nemotron-3-Super-120B-A12B-BF16-8bit is a quantized version of the other (U32/BF16).

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

On the Hub · Downloads on Model Pulse