Nvidia will expand the Nemotron 3 model series and launch Nemotron 3.5 Lightning. Compared with other models in the same category, the output speed of this model can be increased by up to 4 times, and the speed of completing agent tasks can be increased by 30%. Nvidia refers to the Nemotron 3.5 Lightning as “the most efficient model of its kind for long-running intelligent AI workloads.” Nemotron 3.5 Lightning is a hybrid expert model with 30 billion parameters to help develop smarter and more efficient smart body applications. Nemotron 3.5 Lightning is now available as Nvidia's NIM microservice on Hugging Face, ModelScope, OpenRouter, and Build.Nvidia.com.

Nvidia will expand the Nemotron 3 model series and launch Nemotron 3.5 Lightning. Compared with other models in the same category, the output speed of this model can be increased by up to 4 times, and the speed of completing agent tasks can be increased by 30%. Nvidia refers to the Nemotron 3.5 Lightning as “the most efficient model of its kind for long-running intelligent AI workloads.” Nemotron 3.5 Lightning is a hybrid expert model with 30 billion parameters to help develop smarter and more efficient smart body applications. Nemotron 3.5 Lightning is now available as Nvidia's NIM microservice on Hugging Face, ModelScope, OpenRouter, and Build.Nvidia.com.