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 1.24.3 Download
ONNX w8a16 Universal QAIRT 2.42, ONNX Runtime 1.24.3 Download
ONNX w8a8 Universal QAIRT 2.42, ONNX Runtime 1.24.3 Download
ONNX w8a8_mixed_int16 Universal QAIRT 2.42, ONNX Runtime 1.24.3 Download
QNN_DLC float Universal QAIRT 2.43 Download
QNN_DLC w8a16 Universal QAIRT 2.43 Download
TFLITE float Universal QAIRT 2.43, TFLite 2.19.1 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® 8 Elite Gen 5 Mobile 5.857 ms 5 - 167 MB NPU
Yolo-X ONNX float Snapdragon® X2 Elite 7.44 ms 14 - 14 MB NPU
Yolo-X ONNX float Snapdragon® X Elite 13.203 ms 14 - 14 MB NPU
Yolo-X ONNX float Snapdragon® 8 Gen 3 Mobile 8.836 ms 5 - 193 MB NPU
Yolo-X ONNX float Qualcomm® QCS8550 (Proxy) 12.855 ms 0 - 26 MB NPU
Yolo-X ONNX float Qualcomm® QCS9075 16.211 ms 5 - 7 MB NPU
Yolo-X ONNX float Snapdragon® 8 Elite For Galaxy Mobile 7.359 ms 0 - 158 MB NPU
Yolo-X ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 10.829 ms 3 - 209 MB NPU
Yolo-X ONNX w8a16 Snapdragon® X2 Elite 12.232 ms 8 - 8 MB NPU
Yolo-X ONNX w8a16 Snapdragon® X Elite 14.475 ms 7 - 7 MB NPU
Yolo-X ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 9.791 ms 3 - 242 MB NPU
Yolo-X ONNX w8a16 Qualcomm® QCS6490 799.385 ms 113 - 116 MB CPU
Yolo-X ONNX w8a16 Qualcomm® QCS8550 (Proxy) 13.651 ms 0 - 11 MB NPU
Yolo-X ONNX w8a16 Qualcomm® QCS9075 14.604 ms 2 - 5 MB NPU
Yolo-X ONNX w8a16 Qualcomm® QCM6690 421.096 ms 112 - 122 MB CPU
Yolo-X ONNX w8a16 Snapdragon® 8 Elite For Galaxy Mobile 8.594 ms 0 - 204 MB NPU
Yolo-X ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 396.304 ms 112 - 122 MB CPU
Yolo-X ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 8.109 ms 1 - 59 MB NPU
Yolo-X ONNX w8a8 Snapdragon® X2 Elite 8.133 ms 8 - 8 MB NPU
Yolo-X ONNX w8a8 Snapdragon® X Elite 9.186 ms 8 - 8 MB NPU
Yolo-X ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 6.134 ms 1 - 90 MB NPU
Yolo-X ONNX w8a8 Qualcomm® QCS6490 109.671 ms 48 - 57 MB CPU
Yolo-X ONNX w8a8 Qualcomm® QCS8550 (Proxy) 8.297 ms 0 - 96 MB NPU
Yolo-X ONNX w8a8 Qualcomm® QCS9075 8.768 ms 1 - 4 MB NPU
Yolo-X ONNX w8a8 Qualcomm® QCM6690 98.312 ms 39 - 50 MB CPU
Yolo-X ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 5.758 ms 1 - 60 MB NPU
Yolo-X ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 95.365 ms 50 - 60 MB CPU
Yolo-X ONNX w8a8_mixed_int16 Snapdragon® 8 Elite Gen 5 Mobile 23.954 ms 10 - 683 MB NPU
Yolo-X ONNX w8a8_mixed_int16 Snapdragon® X2 Elite 25.863 ms 19 - 19 MB NPU
Yolo-X ONNX w8a8_mixed_int16 Snapdragon® X Elite 34.172 ms 16 - 16 MB NPU
Yolo-X ONNX w8a8_mixed_int16 Snapdragon® 8 Gen 3 Mobile 25.005 ms 12 - 856 MB NPU
Yolo-X ONNX w8a8_mixed_int16 Qualcomm® QCS6490 323.838 ms 103 - 113 MB CPU
Yolo-X ONNX w8a8_mixed_int16 Qualcomm® QCS8550 (Proxy) 35.923 ms 11 - 15 MB NPU
Yolo-X ONNX w8a8_mixed_int16 Qualcomm® QCS9075 35.658 ms 12 - 14 MB NPU
Yolo-X ONNX w8a8_mixed_int16 Qualcomm® QCM6690 204.623 ms 100 - 112 MB CPU
Yolo-X ONNX w8a8_mixed_int16 Snapdragon® 8 Elite For Galaxy Mobile 21.72 ms 11 - 708 MB NPU
Yolo-X ONNX w8a8_mixed_int16 Snapdragon® 7 Gen 4 Mobile 192.582 ms 111 - 122 MB CPU
Yolo-X QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 2.384 ms 1 - 160 MB NPU
Yolo-X QNN_DLC float Snapdragon® X2 Elite 3.488 ms 5 - 5 MB NPU
Yolo-X QNN_DLC float Snapdragon® X Elite 6.051 ms 5 - 5 MB NPU
Yolo-X QNN_DLC float Snapdragon® 8 Gen 3 Mobile 4.247 ms 5 - 181 MB NPU
Yolo-X QNN_DLC float Qualcomm® QCS8275 (Proxy) 27.63 ms 1 - 155 MB NPU
Yolo-X QNN_DLC float Qualcomm® QCS8550 (Proxy) 5.61 ms 5 - 6 MB NPU
Yolo-X QNN_DLC float Qualcomm® SA8775P 8.442 ms 1 - 159 MB NPU
Yolo-X QNN_DLC float Qualcomm® QCS9075 8.762 ms 5 - 11 MB NPU
Yolo-X QNN_DLC float Qualcomm® QCS8450 (Proxy) 14.853 ms 5 - 212 MB NPU
Yolo-X QNN_DLC float Qualcomm® SA7255P 27.63 ms 1 - 155 MB NPU
Yolo-X QNN_DLC float Qualcomm® SA8295P 11.478 ms 2 - 176 MB NPU
Yolo-X QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 3.162 ms 5 - 162 MB NPU
Yolo-X QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 1.804 ms 2 - 84 MB NPU
Yolo-X QNN_DLC w8a16 Snapdragon® X2 Elite 2.483 ms 2 - 2 MB NPU
Yolo-X QNN_DLC w8a16 Snapdragon® X Elite 5.523 ms 2 - 2 MB NPU
Yolo-X QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 3.311 ms 2 - 108 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® QCS6490 15.041 ms 1 - 5 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® QCS8275 (Proxy) 10.828 ms 1 - 71 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® QCS8550 (Proxy) 5.024 ms 2 - 4 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® SA8775P 5.579 ms 1 - 73 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® QCS9075 5.421 ms 2 - 6 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® QCM6690 46.445 ms 2 - 197 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® QCS8450 (Proxy) 6.446 ms 2 - 108 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® SA7255P 10.828 ms 1 - 71 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® SA8295P 7.045 ms 0 - 69 MB NPU
Yolo-X QNN_DLC w8a16 Snapdragon® 8 Elite For Galaxy Mobile 2.366 ms 2 - 82 MB NPU
Yolo-X QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 6.114 ms 2 - 188 MB NPU
Yolo-X TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 2.377 ms 0 - 174 MB NPU
Yolo-X TFLITE float Snapdragon® 8 Gen 3 Mobile 4.276 ms 0 - 199 MB NPU
Yolo-X TFLITE float Qualcomm® QCS8275 (Proxy) 27.65 ms 0 - 167 MB NPU
Yolo-X TFLITE float Qualcomm® QCS8550 (Proxy) 5.454 ms 0 - 2 MB NPU
Yolo-X TFLITE float Qualcomm® SA8775P 8.476 ms 0 - 173 MB NPU
Yolo-X TFLITE float Qualcomm® QCS9075 8.74 ms 0 - 26 MB NPU
Yolo-X TFLITE float Qualcomm® QCS8450 (Proxy) 14.859 ms 0 - 220 MB NPU
Yolo-X TFLITE float Qualcomm® SA7255P 27.65 ms 0 - 167 MB NPU
Yolo-X TFLITE float Qualcomm® SA8295P 11.455 ms 0 - 188 MB NPU
Yolo-X TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 3.188 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