Rockwell brings NVIDIA’s edge AI to FactoryTalk Design Studio
Rockwell Automation has announced the integration of NVIDIA's Nemotron Nano small language model (SLM) into its FactoryTalk Design Studio and related software product workflows. This move enables generative AI to operate at the industrial edge, targeting real-time intelligence and automation for industries requiring secure, local processing.
Edge-based AI
The partnership with NVIDIA leverages the open-source Nemotron-Nano-9B-v2 model, along with NVIDIA NeMo tools, to deliver generative AI directly to the factory floor. By adapting the AI model for environments with limited computational resources and stringent security requirements, Rockwell aims to address the unique needs of industrial users. The solution is designed to function offline, minimising disruption risks and supporting sensitive deployments that may not be connected to broader networks.
Workflow integration
The new AI capability will be embedded not only into HMI panels and industrial appliances but also desktop integrated development environments (IDEs) and on-premise or private cloud servers. It supports parallel processing and instant reasoning, making it suitable for various operational workflows in design, development, production and maintenance. The SLM is fine-tuned using data from FactoryTalk Design Studio Copilot, which is intended to enhance its relevance and performance for automation professionals.
Data security focus
The SLM offers a solution tailored to industrial scenarios where data security and instant responsiveness are priorities. According to Rockwell, the approach provides improved predictability and control compared to larger language models that typically require substantial data centre infrastructure. Early performance evaluations point to advances in responsiveness and the ability to handle air-gapped deployments, where systems are intentionally isolated from external connectivity to prevent unauthorised access.
"Industrial automation demands AI that works reliably at the edge and in secure environments. By fine-tuning the open NVIDIA Nemotron model with FactoryTalk Design Studio data, we're creating solutions that can be deployed anywhere to help our customers accelerate workflows without compromising predictability or control," said Tony Carrara, FactoryTalk Design Studio Business Manager, Rockwell Automation.
Deployment flexibility
Rockwell's implementation of Nemotron Nano focuses on giving enterprises the option to deploy AI in locations with restricted space and power supply, such as on-site machinery or local servers. This flexibility could be significant for organisations aiming to avoid data transmission outside of their premises or for those with critical infrastructure requirements. Rockwell states that the SLM is suited for both edge and air-gapped setups, extending the reach of AI to scenarios where latency and privacy are major concerns.
"Small language models like NVIDIA Nemotron Nano bring real-time intelligence to where decisions are made-from factory floors to power grids. With NVIDIA Nemotron Nano, enterprises using Rockwell FactoryTalk Design Studio can deploy AI in environments with limited space and power, extending AI from data centres into the heart of real-world operations," said Joey Conway, Senior Director, Generative AI Software for Enterprise, NVIDIA.
