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	0.943 ms	2 - 2 MB	NPU
RTMPose-Body2d	ONNX	float	Snapdragon® X Elite	1.78 ms	38 - 38 MB	NPU
RTMPose-Body2d	ONNX	float	Snapdragon® 8 Gen 3 Mobile	1.377 ms	0 - 59 MB	NPU
RTMPose-Body2d	ONNX	float	Snapdragon® 8 Gen 1 Mobile	3.648 ms	0 - 65 MB	NPU
RTMPose-Body2d	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	2.618 ms	1 - 5 MB	NPU
RTMPose-Body2d	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	1.809 ms	0 - 61 MB	NPU
RTMPose-Body2d	ONNX	float	Qualcomm® QCS8450	3.648 ms	0 - 65 MB	NPU
RTMPose-Body2d	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	2.373 ms	0 - 4 MB	NPU
RTMPose-Body2d	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	1.78 ms	38 - 38 MB	NPU
RTMPose-Body2d	ONNX	float	Qualcomm® Dragonwing™ Q-8750	1.119 ms	0 - 42 MB	NPU
RTMPose-Body2d	ONNX	float	Snapdragon® 8 Elite Mobile	1.119 ms	0 - 42 MB	NPU
RTMPose-Body2d	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	0.95 ms	0 - 41 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Snapdragon® X2 Elite	0.793 ms	1 - 1 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Snapdragon® X Elite	1.84 ms	19 - 19 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	1.2 ms	0 - 89 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Snapdragon® 8 Gen 1 Mobile	2.305 ms	0 - 90 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Qualcomm® Dragonwing™ QCS6490	7.474 ms	3 - 6 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-8275	1.784 ms	0 - 4 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	1.782 ms	0 - 23 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Qualcomm® QCS8450	2.305 ms	0 - 90 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-9075	1.905 ms	0 - 3 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-X7181	1.84 ms	19 - 19 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Qualcomm® Dragonwing™ Q-6690	12.281 ms	2 - 179 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Qualcomm® Dragonwing™ Q-7790	2.435 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	0.763 ms	0 - 60 MB	NPU
RTMPose-Body2d	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	2.435 ms	0 - 170 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Snapdragon® X2 Elite	1.107 ms	1 - 1 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Snapdragon® X Elite	1.888 ms	1 - 1 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	1.371 ms	0 - 54 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	3.598 ms	0 - 62 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	2.52 ms	1 - 4 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	7.597 ms	1 - 32 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	1.799 ms	1 - 2 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Qualcomm® SA8775P	2.45 ms	1 - 36 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Qualcomm® SA8650P	2.45 ms	1 - 36 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Qualcomm® SA8255P	2.45 ms	1 - 36 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Qualcomm® QCS8450	3.598 ms	0 - 62 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	2.278 ms	1 - 3 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	1.888 ms	1 - 1 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	1.098 ms	0 - 33 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Qualcomm® SA7255P	7.597 ms	1 - 32 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Qualcomm® SA8295P	3.584 ms	0 - 34 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Snapdragon® 8 Elite Mobile	1.098 ms	0 - 33 MB	NPU
RTMPose-Body2d	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	0.945 ms	1 - 37 MB	NPU
RTMPose-Body2d	QNN_DLC	w8a16	Snapdragon® X2 Elite	0.933 ms	0 - 0 MB	NPU
RTMPose-Body2d	QNN_DLC	w8a16	Snapdragon® X Elite	1.916 ms	0 - 0 MB	NPU
RTMPose-Body2d	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	1.198 ms	0 - 79 MB	NPU
RTMPose-Body2d	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-8275	1.707 ms	0 - 3 MB	NPU
RTMPose-Body2d	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-8275	3.831 ms	0 - 48 MB	NPU
RTMPose-Body2d	QNN_DLC	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	1.697 ms	0 - 2 MB	NPU
RTMPose-Body2d	QNN_DLC	w8a16	Qualcomm® SA8775P	2.054 ms	0 - 51 MB	NPU
RTMPose-Body2d	QNN_DLC	w8a16	Qualcomm® SA8650P	2.054 ms	0 - 51 MB	NPU
RTMPose-Body2d	QNN_DLC	w8a16	Qualcomm® SA8255P	2.054 ms	0 - 51 MB	NPU
RTMPose-Body2d	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-9075	1.893 ms	2 - 4 MB	NPU
RTMPose-Body2d	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-X7181	1.916 ms	0 - 0 MB	NPU
RTMPose-Body2d	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-8750	0.879 ms	0 - 47 MB	NPU
RTMPose-Body2d	QNN_DLC	w8a16	Qualcomm® SA7255P	3.831 ms	0 - 48 MB	NPU
RTMPose-Body2d	QNN_DLC	w8a16	Snapdragon® 8 Elite Mobile	0.879 ms	0 - 47 MB	NPU
RTMPose-Body2d	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	0.743 ms	0 - 47 MB	NPU
RTMPose-Body2d	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	1.374 ms	0 - 77 MB	NPU
RTMPose-Body2d	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	3.784 ms	1 - 87 MB	NPU
RTMPose-Body2d	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	2.879 ms	1 - 43 MB	NPU
RTMPose-Body2d	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	8.126 ms	1 - 46 MB	NPU
RTMPose-Body2d	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	1.865 ms	0 - 12 MB	NPU
RTMPose-Body2d	TFLITE	float	Qualcomm® SA8775P	2.836 ms	0 - 47 MB	NPU
RTMPose-Body2d	TFLITE	float	Qualcomm® SA8650P	2.836 ms	0 - 47 MB	NPU
RTMPose-Body2d	TFLITE	float	Qualcomm® SA8255P	2.836 ms	0 - 47 MB	NPU
RTMPose-Body2d	TFLITE	float	Qualcomm® QCS8450	3.784 ms	1 - 87 MB	NPU
RTMPose-Body2d	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	2.68 ms	0 - 41 MB	NPU
RTMPose-Body2d	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	1.154 ms	0 - 45 MB	NPU
RTMPose-Body2d	TFLITE	float	Qualcomm® SA7255P	8.126 ms	1 - 46 MB	NPU
RTMPose-Body2d	TFLITE	float	Qualcomm® SA8295P	4.088 ms	1 - 48 MB	NPU
RTMPose-Body2d	TFLITE	float	Snapdragon® 8 Elite Mobile	1.154 ms	0 - 45 MB	NPU
RTMPose-Body2d	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	0.993 ms	0 - 45 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.