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: Model_use_case.object_detection
  • Model Stats:
    • Model checkpoint: YOLO11-N
    • Input resolution: 640x640
    • Number of parameters: None
    • Model size (float): None
    • Model size (w8a8): 2.83 MB
Model Precision Device Chipset Target Runtime Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit Target Model
YOLOv11-Detection float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) TFLITE 16.214 ms 0 - 26 MB NPU --
YOLOv11-Detection float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN 12.989 ms 3 - 13 MB NPU --
YOLOv11-Detection float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 9.236 ms 0 - 40 MB NPU --
YOLOv11-Detection float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN 7.757 ms 5 - 37 MB NPU --
YOLOv11-Detection float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 5.969 ms 0 - 10 MB NPU --
YOLOv11-Detection float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN 4.292 ms 5 - 7 MB NPU --
YOLOv11-Detection float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 7.33 ms 0 - 27 MB NPU --
YOLOv11-Detection float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN 5.596 ms 0 - 14 MB NPU --
YOLOv11-Detection float SA7255P ADP Qualcomm® SA7255P TFLITE 16.214 ms 0 - 26 MB NPU --
YOLOv11-Detection float SA7255P ADP Qualcomm® SA7255P QNN 12.989 ms 3 - 13 MB NPU --
YOLOv11-Detection float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) TFLITE 5.947 ms 0 - 11 MB NPU --
YOLOv11-Detection float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN 4.335 ms 7 - 9 MB NPU --
YOLOv11-Detection float SA8295P ADP Qualcomm® SA8295P TFLITE 10.333 ms 0 - 26 MB NPU --
YOLOv11-Detection float SA8295P ADP Qualcomm® SA8295P QNN 8.385 ms 0 - 17 MB NPU --
YOLOv11-Detection float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) TFLITE 6.018 ms 0 - 11 MB NPU --
YOLOv11-Detection float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN 4.412 ms 5 - 7 MB NPU --
YOLOv11-Detection float SA8775P ADP Qualcomm® SA8775P TFLITE 7.33 ms 0 - 27 MB NPU --
YOLOv11-Detection float SA8775P ADP Qualcomm® SA8775P QNN 5.596 ms 0 - 14 MB NPU --
YOLOv11-Detection float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile TFLITE 5.966 ms 0 - 12 MB NPU --
YOLOv11-Detection float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile QNN 4.3 ms 5 - 17 MB NPU --
YOLOv11-Detection float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile ONNX 5.511 ms 5 - 33 MB NPU --
YOLOv11-Detection float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 4.306 ms 0 - 41 MB NPU --
YOLOv11-Detection float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN 2.955 ms 5 - 45 MB NPU --
YOLOv11-Detection float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 3.989 ms 3 - 61 MB NPU --
YOLOv11-Detection float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile TFLITE 4.279 ms 0 - 32 MB NPU --
YOLOv11-Detection float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile QNN 2.779 ms 5 - 40 MB NPU --
YOLOv11-Detection float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile ONNX 3.603 ms 4 - 46 MB NPU --
YOLOv11-Detection float Snapdragon X Elite CRD Snapdragon® X Elite QNN 4.772 ms 5 - 5 MB NPU --
YOLOv11-Detection float Snapdragon X Elite CRD Snapdragon® X Elite ONNX 6.187 ms 5 - 5 MB NPU --
YOLOv11-Detection w8a16 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile ONNX 11.678 ms 0 - 37 MB NPU --
YOLOv11-Detection w8a16 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 8.124 ms 3 - 82 MB NPU --
YOLOv11-Detection w8a16 Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile ONNX 6.474 ms 3 - 78 MB NPU --
YOLOv11-Detection w8a16 Snapdragon X Elite CRD Snapdragon® X Elite ONNX 12.305 ms 2 - 2 MB NPU --
YOLOv11-Detection w8a8 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) TFLITE 3.722 ms 0 - 22 MB NPU --
YOLOv11-Detection w8a8 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN 3.701 ms 1 - 11 MB NPU --
YOLOv11-Detection w8a8 QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 2.147 ms 0 - 33 MB NPU --
YOLOv11-Detection w8a8 QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN 2.258 ms 1 - 38 MB NPU --
YOLOv11-Detection w8a8 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 1.835 ms 0 - 9 MB NPU --
YOLOv11-Detection w8a8 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN 1.831 ms 1 - 12 MB NPU --
YOLOv11-Detection w8a8 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 2.288 ms 0 - 24 MB NPU --
YOLOv11-Detection w8a8 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN 2.269 ms 1 - 16 MB NPU --
YOLOv11-Detection w8a8 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) TFLITE 4.101 ms 0 - 29 MB NPU --
YOLOv11-Detection w8a8 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) QNN 5.696 ms 1 - 16 MB NPU --
YOLOv11-Detection w8a8 RB5 (Proxy) Qualcomm® QCS8250 (Proxy) TFLITE 65.34 ms 0 - 12 MB NPU --
YOLOv11-Detection w8a8 SA7255P ADP Qualcomm® SA7255P TFLITE 3.722 ms 0 - 22 MB NPU --
YOLOv11-Detection w8a8 SA7255P ADP Qualcomm® SA7255P QNN 3.701 ms 1 - 11 MB NPU --
YOLOv11-Detection w8a8 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) TFLITE 1.822 ms 0 - 10 MB NPU --
YOLOv11-Detection w8a8 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN 1.825 ms 1 - 4 MB NPU --
YOLOv11-Detection w8a8 SA8295P ADP Qualcomm® SA8295P TFLITE 2.672 ms 0 - 26 MB NPU --
YOLOv11-Detection w8a8 SA8295P ADP Qualcomm® SA8295P QNN 2.61 ms 0 - 20 MB NPU --
YOLOv11-Detection w8a8 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) TFLITE 1.83 ms 0 - 10 MB NPU --
YOLOv11-Detection w8a8 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN 1.839 ms 1 - 4 MB NPU --
YOLOv11-Detection w8a8 SA8775P ADP Qualcomm® SA8775P TFLITE 2.288 ms 0 - 24 MB NPU --
YOLOv11-Detection w8a8 SA8775P ADP Qualcomm® SA8775P QNN 2.269 ms 1 - 16 MB NPU --
YOLOv11-Detection w8a8 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile TFLITE 1.828 ms 0 - 9 MB NPU --
YOLOv11-Detection w8a8 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile QNN 1.836 ms 1 - 13 MB NPU --
YOLOv11-Detection w8a8 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile ONNX 7.89 ms 0 - 32 MB NPU --
YOLOv11-Detection w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 1.222 ms 0 - 31 MB NPU --
YOLOv11-Detection w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN 1.228 ms 1 - 35 MB NPU --
YOLOv11-Detection w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 5.45 ms 1 - 72 MB NPU --
YOLOv11-Detection w8a8 Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile TFLITE 1.112 ms 0 - 29 MB NPU --
YOLOv11-Detection w8a8 Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile QNN 0.888 ms 1 - 32 MB NPU --
YOLOv11-Detection w8a8 Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile ONNX 4.545 ms 1 - 71 MB NPU --
YOLOv11-Detection w8a8 Snapdragon X Elite CRD Snapdragon® X Elite QNN 2.089 ms 1 - 1 MB NPU --
YOLOv11-Detection w8a8 Snapdragon X Elite CRD Snapdragon® X Elite ONNX 8.121 ms 0 - 0 MB 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 isn't deployed by any Inference Provider. 🙋 Ask for provider support