Nemotron
Family of artificial intelligence models developed by Nvidia
From Wikipedia, the free encyclopedia
Nemotron is a family of artificial intelligence models developed by Nvidia. It includes large language models and multimodal models intended for reasoning, computer programming, information retrieval and agentic AI applications. Nvidia has released open model weights, training data, software and training methods for parts of the family.[2][3]
| Nemotron | |
|---|---|
| Developer | Nvidia |
| Release | November 15, 2023 |
| Type | Large language model |
| License | Various Nvidia Open Model License[1] |
| Website | developer |
| Repository | github |
History
Nvidia introduced the Nemotron-3 8B models in November 2023 for enterprise generative artificial intelligence applications.[4] Nemotron-4 340B followed in June 2024 and included base, instruction-tuned and reward models designed partly for generating synthetic data.[5]
Nvidia later introduced Llama Nemotron, a series of reasoning models derived from Meta's Llama models.[6] In December 2025, Nvidia announced the Nemotron 3 generation, beginning with Nemotron 3 Nano.[2] Nemotron 3 Super and Ultra were released in 2026.[7][8]
Models
The Nemotron 3 models use a hybrid architecture combining Mamba, Transformer, and mixture of experts components.[3]
Nano Omni supports text, image, video and audio input.[10] Nemotron models can be downloaded for local deployment or accessed through Nvidia's application programming interfaces and NIM inference services.[11][12]