nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DFlash

Quantization vs nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16. nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DFlash is a quantized version of the other (BF16/U8).

3 derivatives checked

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

On the Hub · Downloads on Model Pulse