nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8

Quantization vs nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16. nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8 is a quantized version of the other (F8_E4M3/BF16).

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

On the Hub · Downloads on Model Pulse