yolo11n-coreml

This model is a CoreML-converted version of Ultralytics/YOLO11n, optimized for running directly on Apple devices.

Model Details

• Author: Riddhiman Rana
• Converted from: Ultralytics YOLOv11n PyTorch model
• Format: .mlpackage (CoreML)
• Architecture: YOLOv11n
• License: AGPL-3.0
• Tags: real-time, object-detection, coreml, mobile

Compatibility

Tested on:

• iPhone 11
• iPhone 12
• iPhone 13 Pro Max
• iPhone 14
• Apple Silicon Macs: M1 & M2 Pro

Achieves real-time inference (~30–60 FPS depending on device and resolution) in on-device vision pipelines.

Intended Use

• Real-time object detection on iOS/macOS using CoreML
• Integration in Swift or SwiftUI apps using VNCoreMLModel

Limitations

• Converted from YOLO11n: optimized for performance, not maximum accuracy
• Works best with common COCO-style classes
• Not trained or optimized for thermal/night vision, medical imaging, or domain-specific use

How to Use

Swift code snippet to load and run the model:

import Vision
import CoreML

let model = try VNCoreMLModel(for: YOLO11n().model)
let request = VNCoreMLRequest(model: model) { request, error in
    // handle results
}

(Ensure .mlpackage is added to Xcode project.)

Sources

• Original PyTorch model: Ultralytics/YOLOv11
• CoreML conversion via coremltools

Citation

If you use this model, cite the original YOLO11N Model:

@misc{yolov11,
  author = {Ultralytics},
  title = {YOLOv11},
  year = 2024,
  url = {https://github.com/ultralytics/ultralytics}
}