"AI agents must be able to cooperate, coordinate, and execute across large contexts and long time periods, and this, says Nvidia, demands a new type of infrastructure, one that is open. The company says it has the answer with its new Nemotron 3 family of open models. Developers and engineers can use the new models to create domain-specific AI agents or applications without having to build a foundation model from scratch."
"Nemotron 3 features what Nvidia calls a "breakthrough hybrid latent mixture-of-experts (MoE) architecture". The model comes in three sizes: Nano: The smallest and most "compute-cost-efficient," intended for targeted, highly-efficient tasks like quick information retrieval, software debugging, content summarization, and AI assistant workflows. The 30-billion-parameter model activates 3 billion parameters at a time for speed and has a 1-million-token context window, allowing it to remember and connect information over multi-step tasks."
Nvidia positions Nemotron 3 as an open infrastructure for building domain-specific AI agents that can cooperate, coordinate, and execute across large contexts and long time periods. Nemotron 3 uses a hybrid latent mixture-of-experts (MoE) architecture and comes in Nano, Super, and Ultra sizes to suit different application needs. Developers can build agents or applications without training a foundation model from scratch, and most training data plus reinforcement learning libraries are being released for public use. The Nano targets efficient retrieval and assistant tasks, the Super targets high-accuracy reasoning and multi-agent collaboration, and the Ultra targets large, complex reasoning applications.
Read at Computerworld
Unable to calculate read time
Collection
[
|
...
]