Telit Cinterion, an international vendor of turnkey IoT products, launched its innovative Edge AI Software Development Kit (SDK) together with the upcoming release of AI-powered cellular modules for 4G, 5G RedCap, and advanced 5G modules anticipated for Q4 2026. The new SDK offers integration of the compact LiteRT (formerly TensorFlow Lite) runtime into the Linux-based firmware of the modules, allowing machine learning algorithms to operate on the module application processor without additional hardware acceleration or recoding. This streamlined system decreases the complexity of implementation and ensures energy efficiency, using no more than 17% CPU capacity during testing with tasks such as object recognition, predictive maintenance, acoustic analysis, and smart metering. By eliminating the necessity for companion processors, Telit Cinterion allows developers to deploy standard .tflite model files directly onto connected devices without compromising network reliability.
Also Read: Ericsson Partners with Future Technologies to Expand Wireless Infrastructure
Underscoring the strategic shift toward streamlined architecture, Marco Argenton, senior vice president of product management at Telit Cinterion, stated, “Industrial IoT teams should not have to redesign their entire device architecture to add practical AI capabilities. By bringing a lightweight AI runtime into the cellular module, we help customers reduce system complexity and accelerate the path from proof of concept to a connected industrial solution that can operate reliably in the field.” Reinforcing this focus on execution, Vishal Batra, vice president of software engineering at Telit Cinterion, added, “The real engineering challenge isn’t simply running AI at the edge. It’s delivering secure, efficient and reliable intelligence within the constraints of a connected embedded device. Our edge AI SDK enables developers to deploy standard AI models directly on Telit Cinterion modules, accelerating development without compromising the trusted connectivity industrial IoT applications require.”
