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 1.27.1	Download
ONNX	w8a16	Universal	QAIRT 2.45, ONNX Runtime 1.27.1	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
• Model size (float): 68.5 MB
• Model size (w8a16): 18.2 MB
• Number of parameters: 17.9M

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
RTMPose-Body2d	ONNX	float	Snapdragon® X2 Elite	0.936 ms	2 - 2 MB	NPU
RTMPose-Body2d	ONNX	float	Snapdragon® X Elite	1.779 ms	37 - 37 MB	NPU
RTMPose-Body2d	ONNX	float	Snapdragon® 8 Gen 3 Mobile	1.375 ms	0 - 60 MB	NPU
RTMPose-Body2d	ONNX	float	Snapdragon® 8 Gen 1 Mobile	3.654 ms	0 - 66 MB	NPU
RTMPose-Body2d	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	2.654 ms	1 - 5 MB	NPU
RTMPose-Body2d	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	1.81 ms	0 - 41 MB	NPU
RTMPose-Body2d	ONNX	float	Qualcomm® QCS8450	3.654 ms	0 - 66 MB	NPU
RTMPose-Body2d	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	2.339 ms	0 - 4 MB	NPU
RTMPose-Body2d	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	1.779 ms	37 - 37 MB	NPU
RTMPose-Body2d	ONNX	float	Qualcomm® Dragonwing™ Q-8750	1.105 ms	0 - 40 MB	NPU
RTMPose-Body2d	ONNX	float	Snapdragon® 8 Elite Mobile	1.105 ms	0 - 40 MB	NPU
RTMPose-Body2d	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	0.95 ms	0 - 42 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Snapdragon® X2 Elite	0.792 ms	1 - 1 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Snapdragon® X Elite	1.838 ms	20 - 20 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	1.198 ms	0 - 91 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Snapdragon® 8 Gen 1 Mobile	2.288 ms	0 - 90 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Qualcomm® Dragonwing™ QCS6490	7.444 ms	2 - 5 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-8275	1.78 ms	0 - 4 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	1.778 ms	0 - 22 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Qualcomm® QCS8450	2.288 ms	0 - 90 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-9075	1.917 ms	0 - 3 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-X7181	1.838 ms	20 - 20 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Qualcomm® Dragonwing™ Q-6690	12.315 ms	2 - 180 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Qualcomm® Dragonwing™ Q-7790	2.468 ms	0 - 170 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Qualcomm® Dragonwing™ Q-8750	0.894 ms	0 - 62 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Snapdragon® 8 Elite Mobile	0.894 ms	0 - 62 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	0.762 ms	0 - 61 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	2.468 ms	0 - 170 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Snapdragon® X2 Elite	1.119 ms	1 - 1 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Snapdragon® X Elite	1.89 ms	1 - 1 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	1.367 ms	0 - 54 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	3.626 ms	0 - 63 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	2.538 ms	1 - 4 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	7.577 ms	1 - 32 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	1.803 ms	1 - 7 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Qualcomm® SA8775P	2.429 ms	1 - 35 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Qualcomm® SA8650P	2.429 ms	1 - 35 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Qualcomm® SA8255P	2.429 ms	1 - 35 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Qualcomm® QCS8450	3.626 ms	0 - 63 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	2.281 ms	1 - 3 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	1.89 ms	1 - 1 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	1.11 ms	1 - 36 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Qualcomm® SA7255P	7.577 ms	1 - 32 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Qualcomm® SA8295P	3.597 ms	0 - 35 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Snapdragon® 8 Elite Mobile	1.11 ms	1 - 36 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	0.945 ms	1 - 35 MB	NPU
RTMPose-Body2d	QNN_DLC	w8a16	Snapdragon® X2 Elite	0.93 ms	0 - 0 MB	NPU
RTMPose-Body2d	QNN_DLC	w8a16	Snapdragon® X Elite	1.901 ms	0 - 0 MB	NPU
RTMPose-Body2d	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	1.198 ms	0 - 76 MB	NPU
RTMPose-Body2d	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-8275	1.712 ms	0 - 3 MB	NPU
RTMPose-Body2d	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-8275	3.849 ms	0 - 48 MB	NPU
RTMPose-Body2d	QNN_DLC	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	1.703 ms	0 - 20 MB	NPU
RTMPose-Body2d	QNN_DLC	w8a16	Qualcomm® SA8775P	2.061 ms	0 - 51 MB	NPU
RTMPose-Body2d	QNN_DLC	w8a16	Qualcomm® SA8650P	2.061 ms	0 - 51 MB	NPU
RTMPose-Body2d	QNN_DLC	w8a16	Qualcomm® SA8255P	2.061 ms	0 - 51 MB	NPU
RTMPose-Body2d	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-9075	1.889 ms	0 - 2 MB	NPU
RTMPose-Body2d	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-X7181	1.901 ms	0 - 0 MB	NPU
RTMPose-Body2d	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-8750	0.879 ms	0 - 48 MB	NPU
RTMPose-Body2d	QNN_DLC	w8a16	Qualcomm® SA7255P	3.849 ms	0 - 48 MB	NPU
RTMPose-Body2d	QNN_DLC	w8a16	Snapdragon® 8 Elite Mobile	0.879 ms	0 - 48 MB	NPU
RTMPose-Body2d	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	0.745 ms	0 - 46 MB	NPU
RTMPose-Body2d	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	1.375 ms	0 - 77 MB	NPU
RTMPose-Body2d	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	3.772 ms	0 - 85 MB	NPU
RTMPose-Body2d	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	2.87 ms	1 - 43 MB	NPU
RTMPose-Body2d	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	8.132 ms	1 - 46 MB	NPU
RTMPose-Body2d	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	1.861 ms	0 - 3 MB	NPU
RTMPose-Body2d	TFLITE	float	Qualcomm® SA8775P	2.827 ms	0 - 48 MB	NPU
RTMPose-Body2d	TFLITE	float	Qualcomm® SA8650P	2.827 ms	0 - 48 MB	NPU
RTMPose-Body2d	TFLITE	float	Qualcomm® SA8255P	2.827 ms	0 - 48 MB	NPU
RTMPose-Body2d	TFLITE	float	Qualcomm® QCS8450	3.772 ms	0 - 85 MB	NPU
RTMPose-Body2d	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	2.935 ms	1 - 41 MB	NPU
RTMPose-Body2d	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	1.144 ms	0 - 45 MB	NPU
RTMPose-Body2d	TFLITE	float	Qualcomm® SA7255P	8.132 ms	1 - 46 MB	NPU
RTMPose-Body2d	TFLITE	float	Qualcomm® SA8295P	4.09 ms	1 - 48 MB	NPU
RTMPose-Body2d	TFLITE	float	Snapdragon® 8 Elite Mobile	1.144 ms	0 - 45 MB	NPU
RTMPose-Body2d	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	0.981 ms	0 - 47 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.