Rockwell Automation has announced a major leap in industrial intelligence with the integration of NVIDIA’s Nemotron Nano small language model (SLM) into its FactoryTalk Design Studio and other product ecosystems. The move brings generative AI directly to the industrial edge — enabling faster, more secure, and locally deployed intelligence across manufacturing environments.

Developed in collaboration with NVIDIA, the new solution leverages the open-source Nemotron-Nano-9B-v2 model and NVIDIA NeMo framework to deliver powerful AI capabilities in compact, energy-efficient edge environments. The model’s design allows it to run on human-machine interface (HMI) panels, appliances, desktop IDEs, and private cloud systems — even in air-gapped or offline scenarios where real-time decision-making and security are critical.

By fine-tuning the model with data from FactoryTalk Design Studio Copilot, Rockwell has created a generative AI system optimized for design, development, and production workflows. Early tests have shown significant performance gains in reasoning and responsiveness, setting a new standard for AI deployment in industrial settings.

“Industrial automation demands AI that works reliably at the edge and in secure environments,” said Tony Carrara, FactoryTalk Design Studio business manager at Rockwell Automation. “By fine-tuning the open NVIDIA Nemotron model with FactoryTalk data, we’re accelerating workflows without compromising predictability or control.”

NVIDIA’s Joey Conway added, “Small language models like Nemotron Nano bring real-time intelligence to where decisions are made — from factory floors to power grids.”

Rockwell will debut the innovation at Automation Fair 2025 in Chicago from November 17–20, where it will demonstrate how edge-based generative AI is transforming industrial automation.