RTMPose-Body2d: Optimized for Qualcomm Devices

RTMPose is a machine learning model that detects human pose and returns a location and confidence for each of 133 joints.

This is based on the implementation of RTMPose-Body2d 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 2.45, ONNX Runtime 1.25.0	Download
ONNX	w8a16	Universal	QAIRT 2.45, ONNX Runtime 1.25.0	Download
QNN_DLC	float	Universal	QAIRT 2.45	Download
QNN_DLC	w8a16	Universal	QAIRT 2.45	Download
TFLITE	float	Universal	QAIRT 2.45	Download

For more device-specific assets and performance metrics, visit RTMPose-Body2d 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 RTMPose-Body2d on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.pose_estimation

Model Stats:

• Input resolution: 256x192
• Number of parameters: 17.9M
• Model size (float): 68.5 MB
• Model size (w8a16): 18.2 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
RTMPose-Body2d	ONNX	float	Snapdragon® X2 Elite	0.905 ms	212 - 212 MB	NPU
RTMPose-Body2d	ONNX	float	Snapdragon® X Elite	1.717 ms	148 - 148 MB	NPU
RTMPose-Body2d	ONNX	float	Snapdragon® 8 Gen 3 Mobile	1.328 ms	0 - 48 MB	NPU
RTMPose-Body2d	ONNX	float	Snapdragon® 8 Gen 1 Mobile	3.575 ms	1 - 56 MB	NPU
RTMPose-Body2d	ONNX	float	Qualcomm® QCS8550 (Proxy)	1.788 ms	0 - 46 MB	NPU
RTMPose-Body2d	ONNX	float	Qualcomm® QCS8450	3.575 ms	1 - 56 MB	NPU
RTMPose-Body2d	ONNX	float	Snapdragon® 8 Elite Mobile	1.077 ms	0 - 37 MB	NPU
RTMPose-Body2d	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	0.919 ms	1 - 33 MB	NPU
RTMPose-Body2d	ONNX	float	Qualcomm® QCS9075	2.435 ms	1 - 47 MB	NPU
RTMPose-Body2d	ONNX	float	Qualcomm® QCS8750	1.077 ms	0 - 37 MB	NPU
RTMPose-Body2d	ONNX	float	Qualcomm® QCS7181	1.717 ms	148 - 148 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Snapdragon® X2 Elite	0.768 ms	183 - 183 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Snapdragon® X Elite	1.748 ms	157 - 157 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	1.135 ms	0 - 82 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Snapdragon® 8 Gen 1 Mobile	2.153 ms	0 - 78 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Qualcomm® QCS6490	5.137 ms	1 - 47 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	1.692 ms	0 - 23 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Qualcomm® QCS8450	2.153 ms	0 - 78 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Qualcomm® QCS9075	1.903 ms	0 - 45 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	0.731 ms	0 - 55 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Snapdragon® 8 Elite Mobile	0.855 ms	0 - 62 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Qualcomm® QCM6690	11.915 ms	0 - 173 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	2.227 ms	0 - 167 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Qualcomm® QCS7790	2.227 ms	0 - 167 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Qualcomm® QCS8750	0.855 ms	0 - 62 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Qualcomm® QCS7181	1.748 ms	157 - 157 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Snapdragon® X2 Elite	1.028 ms	1 - 1 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Snapdragon® X Elite	1.804 ms	1 - 1 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	1.317 ms	0 - 55 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	3.493 ms	0 - 63 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Qualcomm® QCS8275	7.476 ms	1 - 33 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	1.729 ms	1 - 2 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Qualcomm® QCS8450	3.493 ms	0 - 63 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Snapdragon® 8 Elite Mobile	1.07 ms	0 - 35 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Qualcomm® SA8295P	3.523 ms	1 - 35 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	0.89 ms	1 - 36 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Qualcomm® SA7255P	7.476 ms	1 - 33 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Qualcomm® QCS9075	2.367 ms	1 - 3 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Qualcomm® QCS8750	1.07 ms	0 - 35 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Qualcomm® QCS7181	1.804 ms	1 - 1 MB	NPU
RTMPose-Body2d	QNN_DLC	w8a16	Snapdragon® X2 Elite	0.932 ms	0 - 0 MB	NPU
RTMPose-Body2d	QNN_DLC	w8a16	Snapdragon® X Elite	1.917 ms	0 - 0 MB	NPU
RTMPose-Body2d	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	1.196 ms	0 - 72 MB	NPU
RTMPose-Body2d	QNN_DLC	w8a16	Qualcomm® QCS8275	3.828 ms	0 - 49 MB	NPU
RTMPose-Body2d	QNN_DLC	w8a16	Qualcomm® QCS8550 (Proxy)	1.692 ms	0 - 23 MB	NPU
RTMPose-Body2d	QNN_DLC	w8a16	Qualcomm® QCS9075	1.907 ms	2 - 4 MB	NPU
RTMPose-Body2d	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	0.739 ms	0 - 51 MB	NPU
RTMPose-Body2d	QNN_DLC	w8a16	Snapdragon® 8 Elite Mobile	0.878 ms	0 - 48 MB	NPU
RTMPose-Body2d	QNN_DLC	w8a16	Qualcomm® SA7255P	3.828 ms	0 - 49 MB	NPU
RTMPose-Body2d	QNN_DLC	w8a16	Qualcomm® QCS8750	0.878 ms	0 - 48 MB	NPU
RTMPose-Body2d	QNN_DLC	w8a16	Qualcomm® QCS7181	1.917 ms	0 - 0 MB	NPU
RTMPose-Body2d	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	1.264 ms	0 - 77 MB	NPU
RTMPose-Body2d	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	3.473 ms	0 - 84 MB	NPU
RTMPose-Body2d	TFLITE	float	Qualcomm® QCS8275	7.488 ms	0 - 45 MB	NPU
RTMPose-Body2d	TFLITE	float	Qualcomm® QCS8550 (Proxy)	1.713 ms	0 - 3 MB	NPU
RTMPose-Body2d	TFLITE	float	Qualcomm® SA8775P	19.638 ms	1 - 29 MB	GPU
RTMPose-Body2d	TFLITE	float	Qualcomm® SA8650P	19.638 ms	1 - 29 MB	GPU
RTMPose-Body2d	TFLITE	float	Qualcomm® SA8255P	19.638 ms	1 - 29 MB	GPU
RTMPose-Body2d	TFLITE	float	Qualcomm® QCS8450	3.473 ms	0 - 84 MB	NPU
RTMPose-Body2d	TFLITE	float	Snapdragon® 8 Elite Mobile	1.04 ms	0 - 46 MB	NPU
RTMPose-Body2d	TFLITE	float	Qualcomm® SA8295P	3.521 ms	0 - 47 MB	NPU
RTMPose-Body2d	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	0.89 ms	0 - 47 MB	NPU
RTMPose-Body2d	TFLITE	float	Qualcomm® SA7255P	7.488 ms	0 - 45 MB	NPU
RTMPose-Body2d	TFLITE	float	Qualcomm® QCS9075	2.349 ms	0 - 40 MB	NPU
RTMPose-Body2d	TFLITE	float	Qualcomm® QCS8750	1.04 ms	0 - 46 MB	NPU

License

• The license for the original implementation of RTMPose-Body2d can be found here.

References

• RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose
• 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.