RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-speculator.dflash

Quantization vs nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8. nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8 is a quantized version of the other (F8_E4M3/BF16).

On the Hub · Downloads on Model Pulse