YOLOv11-Detection: Optimized for Qualcomm Devices

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

This is based on the implementation of YOLOv11-Detection found here. This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the Qualcomm® AI Hub Models library to export with custom configurations. More details on model performance across various devices, can be found here.

Qualcomm AI Hub Models uses Qualcomm AI Hub Workbench to compile, profile, and evaluate this model. Sign up to run these models on a hosted Qualcomm® device.

Getting Started

Due to licensing restrictions, we cannot distribute pre-exported model assets for this model. Use the Qualcomm® AI Hub Models Python library to compile and export the model with your own:

  • Custom weights (e.g., fine-tuned checkpoints)
  • Custom input shapes
  • Target device and runtime configurations

See our repository for YOLOv11-Detection on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.object_detection

Model Stats:

  • Model checkpoint: YOLO11-N
  • Input resolution: 640x640
  • Number of parameters: 2.64M
  • Model size (float): 10.1 MB
  • Model size (w8a8): 2.83 MB
  • Model size (w8a16): 3.30 MB

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
YOLOv11-Detection ONNX float Snapdragon® 8 Gen 3 Mobile 3.756 ms 0 - 204 MB NPU
YOLOv11-Detection ONNX float Qualcomm® QCS8550 (Proxy) 5.472 ms 5 - 9 MB NPU
YOLOv11-Detection ONNX float Qualcomm® QCS9075 7.247 ms 5 - 7 MB NPU
YOLOv11-Detection ONNX float Snapdragon® 8 Elite For Galaxy Mobile 3.44 ms 1 - 160 MB NPU
YOLOv11-Detection ONNX float Snapdragon® 8 Elite Gen 5 Mobile 2.651 ms 0 - 156 MB NPU
YOLOv11-Detection ONNX w8a16 Snapdragon® X Elite 5.673 ms 2 - 2 MB NPU
YOLOv11-Detection ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 3.434 ms 0 - 168 MB NPU
YOLOv11-Detection ONNX w8a16 Qualcomm® QCS6490 335.967 ms 92 - 97 MB CPU
YOLOv11-Detection ONNX w8a16 Qualcomm® QCS8550 (Proxy) 5.442 ms 0 - 32 MB NPU
YOLOv11-Detection ONNX w8a16 Qualcomm® QCS9075 6.578 ms 2 - 5 MB NPU
YOLOv11-Detection ONNX w8a16 Qualcomm® QCM6690 168.272 ms 84 - 93 MB CPU
YOLOv11-Detection ONNX w8a16 Snapdragon® 8 Elite For Galaxy Mobile 2.612 ms 0 - 138 MB NPU
YOLOv11-Detection ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 149.516 ms 118 - 128 MB CPU
YOLOv11-Detection ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 2.397 ms 0 - 142 MB NPU
YOLOv11-Detection QNN_DLC float Snapdragon® X Elite 4.326 ms 5 - 5 MB NPU
YOLOv11-Detection QNN_DLC float Snapdragon® 8 Gen 3 Mobile 2.882 ms 0 - 256 MB NPU
YOLOv11-Detection QNN_DLC float Qualcomm® QCS8275 (Proxy) 12.685 ms 0 - 202 MB NPU
YOLOv11-Detection QNN_DLC float Qualcomm® QCS8550 (Proxy) 3.906 ms 2 - 4 MB NPU
YOLOv11-Detection QNN_DLC float Qualcomm® SA8775P 5.28 ms 1 - 203 MB NPU
YOLOv11-Detection QNN_DLC float Qualcomm® QCS9075 4.998 ms 5 - 11 MB NPU
YOLOv11-Detection QNN_DLC float Qualcomm® QCS8450 (Proxy) 8.432 ms 4 - 196 MB NPU
YOLOv11-Detection QNN_DLC float Qualcomm® SA7255P 12.685 ms 0 - 202 MB NPU
YOLOv11-Detection QNN_DLC float Qualcomm® SA8295P 8.576 ms 1 - 166 MB NPU
YOLOv11-Detection QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 2.242 ms 0 - 199 MB NPU
YOLOv11-Detection QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 1.86 ms 5 - 208 MB NPU
YOLOv11-Detection QNN_DLC w8a16 Snapdragon® X Elite 4.639 ms 2 - 2 MB NPU
YOLOv11-Detection QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 2.958 ms 0 - 201 MB NPU
YOLOv11-Detection QNN_DLC w8a16 Qualcomm® QCS8275 (Proxy) 7.9 ms 1 - 174 MB NPU
YOLOv11-Detection QNN_DLC w8a16 Qualcomm® QCS8550 (Proxy) 4.247 ms 2 - 4 MB NPU
YOLOv11-Detection QNN_DLC w8a16 Qualcomm® SA8775P 4.852 ms 1 - 178 MB NPU
YOLOv11-Detection QNN_DLC w8a16 Qualcomm® QCS9075 4.715 ms 2 - 6 MB NPU
YOLOv11-Detection QNN_DLC w8a16 Qualcomm® QCM6690 20.26 ms 2 - 183 MB NPU
YOLOv11-Detection QNN_DLC w8a16 Qualcomm® SA7255P 7.9 ms 1 - 174 MB NPU
YOLOv11-Detection QNN_DLC w8a16 Snapdragon® 8 Elite For Galaxy Mobile 2.089 ms 2 - 182 MB NPU
YOLOv11-Detection QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 4.485 ms 2 - 180 MB NPU
YOLOv11-Detection QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 1.759 ms 2 - 184 MB NPU
YOLOv11-Detection TFLITE float Snapdragon® 8 Gen 3 Mobile 2.605 ms 0 - 186 MB NPU
YOLOv11-Detection TFLITE float Qualcomm® QCS8275 (Proxy) 12.27 ms 0 - 108 MB NPU
YOLOv11-Detection TFLITE float Qualcomm® QCS8550 (Proxy) 3.619 ms 0 - 2 MB NPU
YOLOv11-Detection TFLITE float Qualcomm® SA8775P 5.072 ms 0 - 109 MB NPU
YOLOv11-Detection TFLITE float Qualcomm® QCS9075 4.706 ms 0 - 13 MB NPU
YOLOv11-Detection TFLITE float Qualcomm® QCS8450 (Proxy) 7.114 ms 0 - 76 MB NPU
YOLOv11-Detection TFLITE float Qualcomm® SA7255P 12.27 ms 0 - 108 MB NPU
YOLOv11-Detection TFLITE float Qualcomm® SA8295P 8.04 ms 0 - 52 MB NPU
YOLOv11-Detection TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 1.97 ms 0 - 111 MB NPU
YOLOv11-Detection TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 1.564 ms 0 - 108 MB NPU
YOLOv11-Detection TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 1.105 ms 0 - 55 MB NPU
YOLOv11-Detection TFLITE w8a8 Qualcomm® QCS6490 3.934 ms 0 - 6 MB NPU
YOLOv11-Detection TFLITE w8a8 Qualcomm® QCS8275 (Proxy) 3.414 ms 0 - 40 MB NPU
YOLOv11-Detection TFLITE w8a8 Qualcomm® QCS8550 (Proxy) 1.634 ms 0 - 2 MB NPU
YOLOv11-Detection TFLITE w8a8 Qualcomm® SA8775P 8.182 ms 0 - 42 MB NPU
YOLOv11-Detection TFLITE w8a8 Qualcomm® QCS9075 1.993 ms 0 - 6 MB NPU
YOLOv11-Detection TFLITE w8a8 Qualcomm® QCM6690 7.674 ms 0 - 165 MB NPU
YOLOv11-Detection TFLITE w8a8 Qualcomm® QCS8450 (Proxy) 1.874 ms 0 - 55 MB NPU
YOLOv11-Detection TFLITE w8a8 Qualcomm® SA7255P 3.414 ms 0 - 40 MB NPU
YOLOv11-Detection TFLITE w8a8 Qualcomm® SA8295P 2.479 ms 0 - 38 MB NPU
YOLOv11-Detection TFLITE w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.819 ms 0 - 36 MB NPU
YOLOv11-Detection TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 1.693 ms 0 - 153 MB NPU
YOLOv11-Detection TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.732 ms 0 - 45 MB NPU

License

  • The license for the original implementation of YOLOv11-Detection can be found here.

References

Community

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