Intel reports that more than 500 AI models have been optimized for Core Ultra processors | Technology News

Intel, a US-based semiconductor giant, made a groundbreaking announcement on May 2, revealing that there are now over 500 artificial intelligence (AI) models running optimised on its Core Ultra processors. These AI models are sourced from popular industry platforms such as OpenVINO Model Zoo, Hugging Face, ONNX Model Zoo, and PyTorch.

The optimised AI models cover a wide range of categories including local AI inferencing, such as large language, diffusion, super-resolution, object detection, image classification/segmentation, computer vision, and more. Intel’s Vice President and General Manager of AI and technical marketing in the Client Computing Group, Robert Hallock, expressed pride in surpassing the milestone of 500 pre-trained AI models running optimised on Intel Core Ultra processors. He emphasized Intel’s commitment to providing a robust toolchain for AI developers and a reliable foundation for AI software users.

Explaining the significance of AI models, Intel highlighted their role as critical layers in the software stack that determine the performance, stability, and capabilities of AI-driven applications. By optimising the Intel Core Ultra processors through load-balancing, model compression, and runtime optimization, platforms like OpenVINO enhance the efficiency of AI applications on PC.

With this advancement, developers now have the opportunity to leverage these optimised AI models to create new AI PC features and enhance existing ones. Intel emphasized that the increasing number of AI models running on Intel Core Ultra processors will enable a broader range of AI PC features, opening up new possibilities for innovation in the field of artificial intelligence.