MediaPipe-Hand-Detection: Optimized for Qualcomm Devices

The MediaPipe Hand Landmark Detector is a machine learning pipeline that predicts bounding boxes and pose skeletons of hands in an image.

This is based on the implementation of MediaPipe-Hand-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

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
QNN_DLC	float	Universal	QAIRT 2.45	Download
TFLITE	float	Universal	QAIRT 2.45	Download

For more device-specific assets and performance metrics, visit MediaPipe-Hand-Detection 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 MediaPipe-Hand-Detection on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.object_detection

Model Stats:

• Input resolution: 256x256
• Number of parameters (hand_detector): 1.76M
• Model size (hand_detector) (float): 6.75 MB
• Number of parameters (hand_landmark_detector): 2.01M
• Model size (hand_landmark_detector) (float): 7.70 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
hand_detector	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	0.42 ms	0 - 47 MB	NPU
hand_detector	ONNX	float	Snapdragon® 8 Elite Mobile	0.497 ms	0 - 48 MB	NPU
hand_detector	ONNX	float	Snapdragon® X2 Elite	0.491 ms	0 - 0 MB	NPU
hand_detector	ONNX	float	Snapdragon® X Elite	1.037 ms	3 - 3 MB	NPU
hand_detector	ONNX	float	Snapdragon® X Elite	1.037 ms	3 - 3 MB	NPU
hand_detector	ONNX	float	Snapdragon® 8 Gen 3 Mobile	0.596 ms	0 - 73 MB	NPU
hand_detector	ONNX	float	Qualcomm® QCS8550 (Proxy)	0.834 ms	0 - 7 MB	NPU
hand_detector	ONNX	float	Qualcomm® QCS9075	1.268 ms	1 - 3 MB	NPU
hand_detector	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	0.497 ms	0 - 48 MB	NPU
hand_detector	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	0.377 ms	1 - 43 MB	NPU
hand_detector	QNN_DLC	float	Snapdragon® 8 Elite Mobile	0.439 ms	1 - 39 MB	NPU
hand_detector	QNN_DLC	float	Snapdragon® X2 Elite	0.614 ms	1 - 1 MB	NPU
hand_detector	QNN_DLC	float	Snapdragon® X Elite	0.909 ms	1 - 1 MB	NPU
hand_detector	QNN_DLC	float	Snapdragon® X Elite	0.909 ms	1 - 1 MB	NPU
hand_detector	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	0.535 ms	0 - 58 MB	NPU
hand_detector	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	3.772 ms	1 - 39 MB	NPU
hand_detector	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	0.733 ms	1 - 37 MB	NPU
hand_detector	QNN_DLC	float	Qualcomm® SA8775P	1.274 ms	1 - 42 MB	NPU
hand_detector	QNN_DLC	float	Qualcomm® SA8775P	1.274 ms	1 - 42 MB	NPU
hand_detector	QNN_DLC	float	Qualcomm® SA8775P	1.274 ms	1 - 42 MB	NPU
hand_detector	QNN_DLC	float	Qualcomm® QCS9075	1.114 ms	1 - 3 MB	NPU
hand_detector	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	1.378 ms	0 - 53 MB	NPU
hand_detector	QNN_DLC	float	Qualcomm® SA7255P	3.772 ms	1 - 39 MB	NPU
hand_detector	QNN_DLC	float	Qualcomm® SA8295P	1.697 ms	0 - 31 MB	NPU
hand_detector	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	0.439 ms	1 - 39 MB	NPU
hand_detector	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	0.38 ms	0 - 41 MB	NPU
hand_detector	TFLITE	float	Snapdragon® 8 Elite Mobile	0.447 ms	0 - 35 MB	NPU
hand_detector	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	0.532 ms	0 - 55 MB	NPU
hand_detector	TFLITE	float	Qualcomm® QCS8275 (Proxy)	3.786 ms	0 - 38 MB	NPU
hand_detector	TFLITE	float	Qualcomm® QCS8550 (Proxy)	0.74 ms	0 - 2 MB	NPU
hand_detector	TFLITE	float	Qualcomm® SA8775P	1.302 ms	0 - 39 MB	NPU
hand_detector	TFLITE	float	Qualcomm® SA8775P	1.302 ms	0 - 39 MB	NPU
hand_detector	TFLITE	float	Qualcomm® SA8775P	1.302 ms	0 - 39 MB	NPU
hand_detector	TFLITE	float	Qualcomm® QCS9075	1.128 ms	0 - 7 MB	NPU
hand_detector	TFLITE	float	Qualcomm® QCS8450 (Proxy)	1.385 ms	0 - 50 MB	NPU
hand_detector	TFLITE	float	Qualcomm® SA7255P	3.786 ms	0 - 38 MB	NPU
hand_detector	TFLITE	float	Qualcomm® SA8295P	1.69 ms	0 - 30 MB	NPU
hand_detector	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	0.447 ms	0 - 35 MB	NPU
hand_landmark_detector	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	0.561 ms	0 - 43 MB	NPU
hand_landmark_detector	ONNX	float	Snapdragon® 8 Elite Mobile	0.665 ms	0 - 45 MB	NPU
hand_landmark_detector	ONNX	float	Snapdragon® X2 Elite	0.72 ms	6 - 6 MB	NPU
hand_landmark_detector	ONNX	float	Snapdragon® X Elite	1.393 ms	6 - 6 MB	NPU
hand_landmark_detector	ONNX	float	Snapdragon® X Elite	1.393 ms	6 - 6 MB	NPU
hand_landmark_detector	ONNX	float	Snapdragon® 8 Gen 3 Mobile	0.837 ms	0 - 68 MB	NPU
hand_landmark_detector	ONNX	float	Qualcomm® QCS8550 (Proxy)	1.103 ms	0 - 8 MB	NPU
hand_landmark_detector	ONNX	float	Qualcomm® QCS9075	1.839 ms	1 - 3 MB	NPU
hand_landmark_detector	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	0.665 ms	0 - 45 MB	NPU
hand_landmark_detector	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	0.513 ms	1 - 39 MB	NPU
hand_landmark_detector	QNN_DLC	float	Snapdragon® 8 Elite Mobile	0.601 ms	0 - 34 MB	NPU
hand_landmark_detector	QNN_DLC	float	Snapdragon® X2 Elite	0.843 ms	1 - 1 MB	NPU
hand_landmark_detector	QNN_DLC	float	Snapdragon® X Elite	1.292 ms	1 - 1 MB	NPU
hand_landmark_detector	QNN_DLC	float	Snapdragon® X Elite	1.292 ms	1 - 1 MB	NPU
hand_landmark_detector	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	0.787 ms	0 - 56 MB	NPU
hand_landmark_detector	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	5.338 ms	1 - 34 MB	NPU
hand_landmark_detector	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	1.013 ms	1 - 2 MB	NPU
hand_landmark_detector	QNN_DLC	float	Qualcomm® SA8775P	1.844 ms	1 - 37 MB	NPU
hand_landmark_detector	QNN_DLC	float	Qualcomm® SA8775P	1.844 ms	1 - 37 MB	NPU
hand_landmark_detector	QNN_DLC	float	Qualcomm® SA8775P	1.844 ms	1 - 37 MB	NPU
hand_landmark_detector	QNN_DLC	float	Qualcomm® QCS9075	1.674 ms	3 - 5 MB	NPU
hand_landmark_detector	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	1.952 ms	0 - 52 MB	NPU
hand_landmark_detector	QNN_DLC	float	Qualcomm® SA7255P	5.338 ms	1 - 34 MB	NPU
hand_landmark_detector	QNN_DLC	float	Qualcomm® SA8295P	2.245 ms	0 - 31 MB	NPU
hand_landmark_detector	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	0.601 ms	0 - 34 MB	NPU
hand_landmark_detector	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	0.506 ms	0 - 43 MB	NPU
hand_landmark_detector	TFLITE	float	Snapdragon® 8 Elite Mobile	0.604 ms	0 - 37 MB	NPU
hand_landmark_detector	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	0.767 ms	0 - 58 MB	NPU
hand_landmark_detector	TFLITE	float	Qualcomm® QCS8275 (Proxy)	5.353 ms	0 - 39 MB	NPU
hand_landmark_detector	TFLITE	float	Qualcomm® QCS8550 (Proxy)	0.997 ms	0 - 2 MB	NPU
hand_landmark_detector	TFLITE	float	Qualcomm® SA8775P	1.889 ms	0 - 43 MB	NPU
hand_landmark_detector	TFLITE	float	Qualcomm® SA8775P	1.889 ms	0 - 43 MB	NPU
hand_landmark_detector	TFLITE	float	Qualcomm® SA8775P	1.889 ms	0 - 43 MB	NPU
hand_landmark_detector	TFLITE	float	Qualcomm® QCS9075	1.723 ms	0 - 9 MB	NPU
hand_landmark_detector	TFLITE	float	Qualcomm® QCS8450 (Proxy)	1.96 ms	0 - 56 MB	NPU
hand_landmark_detector	TFLITE	float	Qualcomm® SA7255P	5.353 ms	0 - 39 MB	NPU
hand_landmark_detector	TFLITE	float	Qualcomm® SA8295P	2.229 ms	0 - 35 MB	NPU
hand_landmark_detector	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	0.604 ms	0 - 37 MB	NPU

License

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

References

• MediaPipe Hands: On-device Real-time Hand Tracking
• Source Model Implementation

Community

• Join our AI Hub Slack community to collaborate, post questions and learn more about on-device AI.
• For questions or feedback please reach out to us.