Learn how to export Ultralytics YOLO11 models to Apple’s CoreML format for faster inference on iOS and MacBooks. This tutorial covers the entire workflow: exploring CoreML features, comparing performance with PyTorch, and implementing real-time inference using webcam and video input. You’ll see how to draw FPS on video frames, export YOLO11 to CoreML, and run comparisons between CoreML and PyTorch models, ideal for developers building AI apps for iPhone, iPad, or macOS. Chapters 00:00 - Introduction to CoreML export for YOLO models 00:43 - CoreML Integration documentation walkthrough 01:30 - Key features of CoreML models + speed comparison code overview 02:40 - Boosting performance further with the TensorRT engine format 03:22 - Drawing text (fps + processing time) on video frames: code overview 03:39 - CoreML inference with Ultralytics framework code walkthrough 05:52 - Comparing inference with YOLO11 PyTorch model 06:35 - Exporting YOLO11 model to CoreML format (step-by-step) 07:38 - Running inference with exported YOLO11 CoreML model 08:38 - Real-time inference with YOLO11 PyTorch vs CoreML models (webcam) 09:43 - Conclusion and key takeaways Read more ➡️ Ultralytics YOLO Resources: 💻 GitHub Repository: 📚 Documentation: #coreml #yolo11 #ultralytics #objectdetection #computervision #machinelearning