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® X Elite 13.178 ms 14 - 14 MB NPU
Yolo-X ONNX float Snapdragon® 8 Gen 3 Mobile 8.841 ms 0 - 187 MB NPU
Yolo-X ONNX float Qualcomm® QCS8550 (Proxy) 13.149 ms 0 - 17 MB NPU
Yolo-X ONNX float Qualcomm® QCS9075 16.154 ms 5 - 7 MB NPU
Yolo-X ONNX float Snapdragon® 8 Elite For Galaxy Mobile 7.37 ms 3 - 164 MB NPU
Yolo-X ONNX float Snapdragon® 8 Elite Gen 5 Mobile 5.87 ms 5 - 166 MB NPU
Yolo-X ONNX float Snapdragon® X2 Elite 8.62 ms 14 - 14 MB NPU
Yolo-X ONNX w8a16 Snapdragon® X Elite 14.5 ms 7 - 7 MB NPU
Yolo-X ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 9.752 ms 3 - 241 MB NPU
Yolo-X ONNX w8a16 Qualcomm® QCS6490 811.041 ms 113 - 116 MB CPU
Yolo-X ONNX w8a16 Qualcomm® QCS8550 (Proxy) 13.537 ms 0 - 12 MB NPU
Yolo-X ONNX w8a16 Qualcomm® QCS9075 14.368 ms 2 - 5 MB NPU
Yolo-X ONNX w8a16 Qualcomm® QCM6690 423.273 ms 99 - 109 MB CPU
Yolo-X ONNX w8a16 Snapdragon® 8 Elite For Galaxy Mobile 8.728 ms 0 - 205 MB NPU
Yolo-X ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 396.04 ms 112 - 122 MB CPU
Yolo-X ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 10.751 ms 3 - 210 MB NPU
Yolo-X ONNX w8a16 Snapdragon® X2 Elite 11.183 ms 8 - 8 MB NPU
Yolo-X ONNX w8a8 Snapdragon® X Elite 9.065 ms 8 - 8 MB NPU
Yolo-X ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 6.108 ms 1 - 90 MB NPU
Yolo-X ONNX w8a8 Qualcomm® QCS6490 107.7 ms 48 - 57 MB CPU
Yolo-X ONNX w8a8 Qualcomm® QCS8550 (Proxy) 8.228 ms 0 - 114 MB NPU
Yolo-X ONNX w8a8 Qualcomm® QCS9075 8.775 ms 1 - 4 MB NPU
Yolo-X ONNX w8a8 Qualcomm® QCM6690 97.744 ms 38 - 49 MB CPU
Yolo-X ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 5.753 ms 1 - 60 MB NPU
Yolo-X ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 93.66 ms 49 - 60 MB CPU
Yolo-X ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 8.013 ms 1 - 59 MB NPU
Yolo-X ONNX w8a8 Snapdragon® X2 Elite 8.163 ms 8 - 8 MB NPU
Yolo-X ONNX w8a8_mixed_int16 Snapdragon® X Elite 50.347 ms 34 - 34 MB NPU
Yolo-X ONNX w8a8_mixed_int16 Snapdragon® 8 Gen 3 Mobile 36.391 ms 25 - 1233 MB NPU
Yolo-X ONNX w8a8_mixed_int16 Qualcomm® QCS6490 324.708 ms 105 - 112 MB CPU
Yolo-X ONNX w8a8_mixed_int16 Qualcomm® QCS8550 (Proxy) 50.982 ms 22 - 26 MB NPU
Yolo-X ONNX w8a8_mixed_int16 Qualcomm® QCM6690 206.948 ms 96 - 107 MB CPU
Yolo-X ONNX w8a8_mixed_int16 Snapdragon® 8 Elite For Galaxy Mobile 31.855 ms 27 - 865 MB NPU
Yolo-X ONNX w8a8_mixed_int16 Snapdragon® 7 Gen 4 Mobile 193.83 ms 105 - 116 MB CPU
Yolo-X ONNX w8a8_mixed_int16 Snapdragon® 8 Elite Gen 5 Mobile 32.263 ms 24 - 1155 MB NPU
Yolo-X ONNX w8a8_mixed_int16 Snapdragon® X2 Elite 37.979 ms 34 - 34 MB NPU
Yolo-X QNN_DLC float Snapdragon® X Elite 6.068 ms 5 - 5 MB NPU
Yolo-X QNN_DLC float Snapdragon® 8 Gen 3 Mobile 4.261 ms 5 - 181 MB NPU
Yolo-X QNN_DLC float Qualcomm® QCS8275 (Proxy) 27.629 ms 0 - 154 MB NPU
Yolo-X QNN_DLC float Qualcomm® QCS8550 (Proxy) 5.638 ms 5 - 99 MB NPU
Yolo-X QNN_DLC float Qualcomm® SA8775P 8.432 ms 0 - 158 MB NPU
Yolo-X QNN_DLC float Qualcomm® QCS9075 8.755 ms 7 - 13 MB NPU
Yolo-X QNN_DLC float Qualcomm® QCS8450 (Proxy) 14.877 ms 3 - 209 MB NPU
Yolo-X QNN_DLC float Qualcomm® SA7255P 27.629 ms 0 - 154 MB NPU
Yolo-X QNN_DLC float Qualcomm® SA8295P 11.454 ms 0 - 175 MB NPU
Yolo-X QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 3.157 ms 0 - 159 MB NPU
Yolo-X QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 2.382 ms 5 - 164 MB NPU
Yolo-X QNN_DLC float Snapdragon® X2 Elite 3.421 ms 5 - 5 MB NPU
Yolo-X QNN_DLC w8a16 Snapdragon® X Elite 5.498 ms 2 - 2 MB NPU
Yolo-X QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 3.282 ms 2 - 104 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® QCS6490 14.529 ms 3 - 7 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® QCS8275 (Proxy) 10.828 ms 1 - 72 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® QCS8550 (Proxy) 5.007 ms 2 - 15 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® SA8775P 5.559 ms 1 - 73 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® QCS9075 5.428 ms 1 - 5 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® QCM6690 45.8 ms 3 - 198 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® QCS8450 (Proxy) 6.493 ms 2 - 111 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® SA7255P 10.828 ms 1 - 72 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® SA8295P 6.993 ms 0 - 70 MB NPU
Yolo-X QNN_DLC w8a16 Snapdragon® 8 Elite For Galaxy Mobile 2.345 ms 2 - 82 MB NPU
Yolo-X QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 6.046 ms 2 - 189 MB NPU
Yolo-X QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 1.805 ms 2 - 82 MB NPU
Yolo-X QNN_DLC w8a16 Snapdragon® X2 Elite 2.955 ms 2 - 2 MB NPU
Yolo-X TFLITE float Snapdragon® 8 Gen 3 Mobile 4.264 ms 0 - 201 MB NPU
Yolo-X TFLITE float Qualcomm® QCS8275 (Proxy) 27.644 ms 0 - 166 MB NPU
Yolo-X TFLITE float Qualcomm® QCS8550 (Proxy) 5.632 ms 0 - 3 MB NPU
Yolo-X TFLITE float Qualcomm® SA8775P 8.467 ms 0 - 171 MB NPU
Yolo-X TFLITE float Qualcomm® QCS9075 8.733 ms 0 - 26 MB NPU
Yolo-X TFLITE float Qualcomm® QCS8450 (Proxy) 14.881 ms 0 - 220 MB NPU
Yolo-X TFLITE float Qualcomm® SA7255P 27.644 ms 0 - 166 MB NPU
Yolo-X TFLITE float Qualcomm® SA8295P 11.496 ms 0 - 188 MB NPU
Yolo-X TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 3.21 ms 0 - 168 MB NPU
Yolo-X TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 2.379 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