YOLOv11-Detection: Optimized for Mobile Deployment

Real-time object detection optimized for mobile and edge by Ultralytics

Ultralytics YOLOv11 is a machine learning model that predicts bounding boxes and classes of objects in an image.

This model is an implementation of YOLOv11-Detection found here.

More details on model performance across various devices, can be found here.

Model Details

  • Model Type: Object detection
  • Model Stats:
    • Model checkpoint: YOLO11-N
    • Input resolution: 640x640
    • Number of parameters: None
    • Model size: None
Model Device Chipset Target Runtime Inference Time (ms) Peak Memory Range (MB) Precision Primary Compute Unit Target Model
YOLOv11-Detection Samsung Galaxy S23 Snapdragon® 8 Gen 2 TFLITE 7.555 ms 0 - 11 MB FP16 NPU --
YOLOv11-Detection Samsung Galaxy S23 Snapdragon® 8 Gen 2 QNN 4.363 ms 6 - 8 MB FP16 NPU --
YOLOv11-Detection Samsung Galaxy S23 Snapdragon® 8 Gen 2 ONNX 6.732 ms 5 - 31 MB FP16 NPU --
YOLOv11-Detection Samsung Galaxy S24 Snapdragon® 8 Gen 3 TFLITE 5.426 ms 0 - 50 MB FP16 NPU --
YOLOv11-Detection Samsung Galaxy S24 Snapdragon® 8 Gen 3 QNN 3.005 ms 5 - 24 MB FP16 NPU --
YOLOv11-Detection Samsung Galaxy S24 Snapdragon® 8 Gen 3 ONNX 4.426 ms 7 - 65 MB FP16 NPU --
YOLOv11-Detection Snapdragon 8 Elite QRD Snapdragon® 8 Elite TFLITE 5.196 ms 0 - 42 MB FP16 NPU --
YOLOv11-Detection Snapdragon 8 Elite QRD Snapdragon® 8 Elite QNN 2.672 ms 5 - 48 MB FP16 NPU --
YOLOv11-Detection Snapdragon 8 Elite QRD Snapdragon® 8 Elite ONNX 4.604 ms 5 - 51 MB FP16 NPU --
YOLOv11-Detection SA7255P ADP SA7255P TFLITE 61.033 ms 0 - 38 MB FP16 NPU --
YOLOv11-Detection SA7255P ADP SA7255P QNN 56.864 ms 0 - 9 MB FP16 NPU --
YOLOv11-Detection SA8255 (Proxy) SA8255P Proxy TFLITE 7.62 ms 0 - 11 MB FP16 NPU --
YOLOv11-Detection SA8255 (Proxy) SA8255P Proxy QNN 4.483 ms 5 - 7 MB FP16 NPU --
YOLOv11-Detection SA8295P ADP SA8295P TFLITE 12.013 ms 0 - 26 MB FP16 NPU --
YOLOv11-Detection SA8295P ADP SA8295P QNN 8.385 ms 0 - 18 MB FP16 NPU --
YOLOv11-Detection SA8650 (Proxy) SA8650P Proxy TFLITE 7.756 ms 0 - 11 MB FP16 NPU --
YOLOv11-Detection SA8650 (Proxy) SA8650P Proxy QNN 4.362 ms 5 - 7 MB FP16 NPU --
YOLOv11-Detection SA8775P ADP SA8775P TFLITE 10.569 ms 0 - 37 MB FP16 NPU --
YOLOv11-Detection SA8775P ADP SA8775P QNN 6.692 ms 0 - 10 MB FP16 NPU --
YOLOv11-Detection QCS8275 (Proxy) QCS8275 Proxy TFLITE 61.033 ms 0 - 38 MB FP16 NPU --
YOLOv11-Detection QCS8275 (Proxy) QCS8275 Proxy QNN 56.864 ms 0 - 9 MB FP16 NPU --
YOLOv11-Detection QCS8550 (Proxy) QCS8550 Proxy TFLITE 7.631 ms 0 - 11 MB FP16 NPU --
YOLOv11-Detection QCS8550 (Proxy) QCS8550 Proxy QNN 4.348 ms 2 - 4 MB FP16 NPU --
YOLOv11-Detection QCS9075 (Proxy) QCS9075 Proxy TFLITE 10.569 ms 0 - 37 MB FP16 NPU --
YOLOv11-Detection QCS9075 (Proxy) QCS9075 Proxy QNN 6.692 ms 0 - 10 MB FP16 NPU --
YOLOv11-Detection QCS8450 (Proxy) QCS8450 Proxy TFLITE 11.133 ms 0 - 40 MB FP16 NPU --
YOLOv11-Detection QCS8450 (Proxy) QCS8450 Proxy QNN 8.024 ms 5 - 39 MB FP16 NPU --
YOLOv11-Detection Snapdragon X Elite CRD Snapdragon® X Elite QNN 4.775 ms 5 - 5 MB FP16 NPU --
YOLOv11-Detection Snapdragon X Elite CRD Snapdragon® X Elite ONNX 6.525 ms 5 - 5 MB FP16 NPU --

License

  • The license for the original implementation of YOLOv11-Detection can be found here.
  • The license for the compiled assets for on-device deployment can be found here

References

Community

Usage and Limitations

Model may not be used for or in connection with any of the following applications:

  • Accessing essential private and public services and benefits;
  • Administration of justice and democratic processes;
  • Assessing or recognizing the emotional state of a person;
  • Biometric and biometrics-based systems, including categorization of persons based on sensitive characteristics;
  • Education and vocational training;
  • Employment and workers management;
  • Exploitation of the vulnerabilities of persons resulting in harmful behavior;
  • General purpose social scoring;
  • Law enforcement;
  • Management and operation of critical infrastructure;
  • Migration, asylum and border control management;
  • Predictive policing;
  • Real-time remote biometric identification in public spaces;
  • Recommender systems of social media platforms;
  • Scraping of facial images (from the internet or otherwise); and/or
  • Subliminal manipulation
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The HF Inference API does not support object-detection models for pytorch library.