500 AI Models Optimised For Core Ultra Processors: Intel

Intel on Thursday said that it has optimised over 500 AI models to run on its Core Ultra processors. This enhancement will enhance the capabilities of devices by integrating a broad spectrum of AI functionalities, from large language and image processing models to object detection and computer vision.

Intel’s Vice President and General Manager of AI and Technical Marketing in the Client Computing Group, Robert Hallock, highlighted this achievement as a milestone in Intel’s long-standing effort to integrate AI applications more seamlessly into everyday technology. According to Hallock, this development not only continues Intel’s rich heritage in client AI but also shows the company’s dedication to providing a reliable foundation for AI software users.

“This unmatched selection reflects our commitment to building not only the PC industry’s most robust toolchain for AI developers, but a rock-solid foundation AI software users can implicitly trust,” he said.

The company detailed that these AI models are optimised to perform efficiently on Intel Core Ultra processors by employing techniques that include load-balancing across all compute units, compressing the models for better operation in AI-driven PCs and enhancing runtime to leverage the processors’ memory bandwidth and core architecture. These optimised models are sourced from well-known industry platforms such as OpenVINO Model Zoo, Hugging Face, ONNX Model Zoo and PyTorch, offering developers a wide range of tools to innovate and integrate AI features into PC applications.

With this broad library of AI models, developers now have the resources to create innovative features that can transform user experiences on PCs. This Intel initiative is looking to not just support the development of new AI-driven applications but also ensure that these technologies are accessible and efficient, making advanced AI functionality a standard feature in the next generation of personal computers.