Hugging Face's logo

qualcomm
/
Yolo-X

Object Detection
PyTorch
real_time
android
Model card Files
xet
Community

Yolo-X: Optimized for Qualcomm Devices

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

This is based on the implementation of Yolo-X 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

There are two ways to deploy this model on your device:

Option 1: Download Pre-Exported Models

Below are pre-exported model assets ready for deployment.

Runtime Precision Chipset SDK Versions Download
ONNX float Universal QAIRT 2.42, ONNX Runtime 1.24.1 Download
ONNX w8a16 Universal QAIRT 2.42, ONNX Runtime 1.24.1 Download
ONNX w8a8 Universal QAIRT 2.42, ONNX Runtime 1.24.1 Download
ONNX w8a8_mixed_int16 Universal QAIRT 2.42, ONNX Runtime 1.24.1 Download
QNN_DLC float Universal QAIRT 2.43 Download
QNN_DLC w8a16 Universal QAIRT 2.43 Download
QNN_DLC w8a8 Universal QAIRT 2.43 Download
QNN_DLC w8a8_mixed_int16 Universal QAIRT 2.43 Download
TFLITE float Universal QAIRT 2.43, TFLite 2.17.0 Download
TFLITE w8a8 Universal QAIRT 2.43, TFLite 2.17.0 Download

For more device-specific assets and performance metrics, visit Yolo-X on Qualcomm® AI Hub.

Option 2: Export with Custom Configurations

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

This option is ideal if you need to customize the model beyond the default configuration provided here.

See our repository for Yolo-X on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.object_detection

Model Stats:

  • Model checkpoint: YoloX Small
  • Input resolution: 640x640
  • Number of parameters: 8.98M
  • Model size (float): 34.3 MB
  • Model size (w8a16): 9.53 MB
  • Model size (w8a8): 8.96 MB

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
Yolo-X ONNX float Snapdragon® X2 Elite 7.287 ms 14 - 14 MB NPU
Yolo-X ONNX float Snapdragon® X Elite 13.258 ms 14 - 14 MB NPU
Yolo-X ONNX float Snapdragon® 8 Gen 3 Mobile 8.853 ms 3 - 184 MB NPU
Yolo-X ONNX float Qualcomm® QCS8550 (Proxy) 13.016 ms 0 - 163 MB NPU
Yolo-X ONNX float Qualcomm® QCS9075 16.339 ms 5 - 7 MB NPU
Yolo-X ONNX float Snapdragon® 8 Elite For Galaxy Mobile 7.364 ms 1 - 159 MB NPU
Yolo-X ONNX float Snapdragon® 8 Elite Gen 5 Mobile 5.855 ms 5 - 167 MB NPU
Yolo-X ONNX w8a16 Snapdragon® X2 Elite 11.103 ms 8 - 8 MB NPU
Yolo-X ONNX w8a16 Snapdragon® X Elite 14.481 ms 7 - 7 MB NPU
Yolo-X ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 9.641 ms 3 - 241 MB NPU
Yolo-X ONNX w8a16 Qualcomm® QCS6490 806.18 ms 113 - 116 MB CPU
Yolo-X ONNX w8a16 Qualcomm® QCS8550 (Proxy) 13.59 ms 0 - 11 MB NPU
Yolo-X ONNX w8a16 Qualcomm® QCS9075 14.485 ms 2 - 5 MB NPU
Yolo-X ONNX w8a16 Qualcomm® QCM6690 420.958 ms 102 - 112 MB CPU
Yolo-X ONNX w8a16 Snapdragon® 8 Elite For Galaxy Mobile 8.626 ms 0 - 199 MB NPU
Yolo-X ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 395.379 ms 113 - 122 MB CPU
Yolo-X ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 10.743 ms 3 - 205 MB NPU
Yolo-X ONNX w8a8 Snapdragon® X2 Elite 8.15 ms 8 - 8 MB NPU
Yolo-X ONNX w8a8 Snapdragon® X Elite 9.074 ms 8 - 8 MB NPU
Yolo-X ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 6.155 ms 1 - 93 MB NPU
Yolo-X ONNX w8a8 Qualcomm® QCS6490 108.293 ms 47 - 57 MB CPU
Yolo-X ONNX w8a8 Qualcomm® QCS8550 (Proxy) 8.226 ms 1 - 39 MB NPU
Yolo-X ONNX w8a8 Qualcomm® QCS9075 8.781 ms 1 - 4 MB NPU
Yolo-X ONNX w8a8 Qualcomm® QCM6690 97.766 ms 40 - 50 MB CPU
Yolo-X ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 5.746 ms 1 - 61 MB NPU
Yolo-X ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 94.911 ms 49 - 59 MB CPU
Yolo-X ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 8.098 ms 1 - 59 MB NPU
Yolo-X ONNX w8a8_mixed_int16 Snapdragon® X2 Elite 25.949 ms 19 - 19 MB NPU
Yolo-X ONNX w8a8_mixed_int16 Snapdragon® X Elite 34.067 ms 16 - 16 MB NPU
Yolo-X ONNX w8a8_mixed_int16 Snapdragon® 8 Gen 3 Mobile 25.444 ms 11 - 855 MB NPU
Yolo-X ONNX w8a8_mixed_int16 Qualcomm® QCS6490 338.044 ms 103 - 112 MB CPU
Yolo-X ONNX w8a8_mixed_int16 Qualcomm® QCS8550 (Proxy) 35.676 ms 4 - 29 MB NPU
Yolo-X ONNX w8a8_mixed_int16 Qualcomm® QCS9075 35.572 ms 11 - 14 MB NPU
Yolo-X ONNX w8a8_mixed_int16 Qualcomm® QCM6690 206.229 ms 104 - 114 MB CPU
Yolo-X ONNX w8a8_mixed_int16 Snapdragon® 8 Elite For Galaxy Mobile 21.917 ms 12 - 721 MB NPU
Yolo-X ONNX w8a8_mixed_int16 Snapdragon® 7 Gen 4 Mobile 192.904 ms 106 - 117 MB CPU
Yolo-X ONNX w8a8_mixed_int16 Snapdragon® 8 Elite Gen 5 Mobile 24.449 ms 10 - 685 MB NPU
Yolo-X QNN_DLC float Snapdragon® X2 Elite 3.495 ms 5 - 5 MB NPU
Yolo-X QNN_DLC float Snapdragon® X Elite 6.05 ms 5 - 5 MB NPU
Yolo-X QNN_DLC float Snapdragon® 8 Gen 3 Mobile 4.26 ms 5 - 183 MB NPU
Yolo-X QNN_DLC float Qualcomm® QCS8275 (Proxy) 27.639 ms 1 - 154 MB NPU
Yolo-X QNN_DLC float Qualcomm® QCS8550 (Proxy) 5.571 ms 5 - 112 MB NPU
Yolo-X QNN_DLC float Qualcomm® SA8775P 8.462 ms 2 - 160 MB NPU
Yolo-X QNN_DLC float Qualcomm® QCS9075 8.751 ms 5 - 11 MB NPU
Yolo-X QNN_DLC float Qualcomm® QCS8450 (Proxy) 14.86 ms 5 - 211 MB NPU
Yolo-X QNN_DLC float Qualcomm® SA7255P 27.639 ms 1 - 154 MB NPU
Yolo-X QNN_DLC float Qualcomm® SA8295P 11.498 ms 0 - 175 MB NPU
Yolo-X QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 3.163 ms 0 - 154 MB NPU
Yolo-X QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 2.381 ms 5 - 164 MB NPU
Yolo-X QNN_DLC w8a16 Snapdragon® X2 Elite 2.42 ms 2 - 2 MB NPU
Yolo-X QNN_DLC w8a16 Snapdragon® X Elite 5.533 ms 2 - 2 MB NPU
Yolo-X QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 3.281 ms 2 - 109 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® QCS6490 14.928 ms 1 - 5 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® QCS8275 (Proxy) 10.865 ms 0 - 69 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® QCS8550 (Proxy) 5.023 ms 2 - 4 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® SA8775P 5.555 ms 1 - 72 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® QCS9075 5.423 ms 2 - 6 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® QCM6690 45.995 ms 2 - 197 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® QCS8450 (Proxy) 6.638 ms 2 - 110 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® SA7255P 10.865 ms 0 - 69 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® SA8295P 7.073 ms 0 - 70 MB NPU
Yolo-X QNN_DLC w8a16 Snapdragon® 8 Elite For Galaxy Mobile 2.37 ms 2 - 82 MB NPU
Yolo-X QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 5.951 ms 2 - 188 MB NPU
Yolo-X QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 1.801 ms 2 - 84 MB NPU
Yolo-X TFLITE float Snapdragon® 8 Gen 3 Mobile 4.25 ms 0 - 200 MB NPU
Yolo-X TFLITE float Qualcomm® QCS8275 (Proxy) 27.613 ms 0 - 166 MB NPU
Yolo-X TFLITE float Qualcomm® QCS8550 (Proxy) 5.611 ms 0 - 2 MB NPU
Yolo-X TFLITE float Qualcomm® SA8775P 8.476 ms 0 - 170 MB NPU
Yolo-X TFLITE float Qualcomm® QCS9075 8.732 ms 0 - 26 MB NPU
Yolo-X TFLITE float Qualcomm® QCS8450 (Proxy) 14.791 ms 0 - 221 MB NPU
Yolo-X TFLITE float Qualcomm® SA7255P 27.613 ms 0 - 166 MB NPU
Yolo-X TFLITE float Qualcomm® SA8295P 11.492 ms 0 - 189 MB NPU
Yolo-X TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 3.207 ms 0 - 171 MB NPU
Yolo-X TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 2.38 ms 0 - 174 MB NPU

License

  • The license for the original implementation of Yolo-X can be found here.

References

Community

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
Object Detection
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support