soyrsoyr/Nemotron-3.5-Lightning-1.4B-A0.1B-MTP-NVFP4

Quantization vs inference-optimization/Nemotron-3.5-Lightning-1.4B-A0.1B-MTP. soyrsoyr/Nemotron-3.5-Lightning-1.4B-A0.1B-MTP-NVFP4 is a quantized version of the other (BF16/U8).

On the Hub · Downloads on Model Pulse