YOLOv11-Pose: Optimized for Qualcomm Devices

Ultralytics YOLOv11-Pose is a machine learning model that predicts human body keypoints and bounding boxes in an image.

This is based on the implementation of YOLOv11-Pose 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

Due to licensing restrictions, we cannot distribute pre-exported model assets for this model. 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

See our repository for YOLOv11-Pose on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.pose_estimation

Model Stats:

• Model checkpoint: YOLO11-N-Pose
• Input resolution: 640x640
• Number of parameters: 2.9M
• Model size (float): 11.1 MB
• Model size (w8a8_mixed_int16): 5.85 MB
• Model size (w8a16): 3.63 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
YOLOv11-Pose	ONNX	float	Snapdragon® X2 Elite	3.319 ms	208 - 208 MB	NPU
YOLOv11-Pose	ONNX	float	Snapdragon® X Elite	7.586 ms	176 - 176 MB	NPU
YOLOv11-Pose	ONNX	float	Snapdragon® 8 Gen 3 Mobile	6.137 ms	10 - 236 MB	NPU
YOLOv11-Pose	ONNX	float	Snapdragon® 8 Gen 1 Mobile	12.699 ms	9 - 214 MB	NPU
YOLOv11-Pose	ONNX	float	Qualcomm® QCS8550 (Proxy)	7.982 ms	6 - 10 MB	NPU
YOLOv11-Pose	ONNX	float	Qualcomm® QCS8450	12.699 ms	9 - 214 MB	NPU
YOLOv11-Pose	ONNX	float	Snapdragon® 8 Elite Mobile	4.729 ms	5 - 209 MB	NPU
YOLOv11-Pose	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	3.03 ms	3 - 223 MB	NPU
YOLOv11-Pose	ONNX	float	Qualcomm® QCS9075	8.3 ms	4 - 53 MB	NPU
YOLOv11-Pose	ONNX	float	Qualcomm® QCS8750	4.729 ms	5 - 209 MB	NPU
YOLOv11-Pose	ONNX	float	Qualcomm® QCS7181	7.586 ms	176 - 176 MB	NPU
YOLOv11-Pose	ONNX	w8a16	Snapdragon® X2 Elite	2.772 ms	210 - 210 MB	NPU
YOLOv11-Pose	ONNX	w8a16	Snapdragon® X Elite	6.168 ms	147 - 147 MB	NPU
YOLOv11-Pose	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	3.671 ms	2 - 216 MB	NPU
YOLOv11-Pose	ONNX	w8a16	Snapdragon® 8 Gen 1 Mobile	9.558 ms	4 - 219 MB	NPU
YOLOv11-Pose	ONNX	w8a16	Qualcomm® QCS6490	13.791 ms	2 - 48 MB	NPU
YOLOv11-Pose	ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	5.929 ms	3 - 7 MB	NPU
YOLOv11-Pose	ONNX	w8a16	Qualcomm® QCS8450	9.558 ms	4 - 219 MB	NPU
YOLOv11-Pose	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	2.446 ms	0 - 88 MB	NPU
YOLOv11-Pose	ONNX	w8a16	Snapdragon® 8 Elite Mobile	2.77 ms	0 - 90 MB	NPU
YOLOv11-Pose	ONNX	w8a16	Qualcomm® QCS9075	6.718 ms	2 - 48 MB	NPU
YOLOv11-Pose	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	7.529 ms	4 - 199 MB	NPU
YOLOv11-Pose	ONNX	w8a16	Qualcomm® QCM6690	27.844 ms	4 - 201 MB	NPU
YOLOv11-Pose	ONNX	w8a16	Qualcomm® QCS7790	7.529 ms	4 - 199 MB	NPU
YOLOv11-Pose	ONNX	w8a16	Qualcomm® QCS8750	2.77 ms	0 - 90 MB	NPU
YOLOv11-Pose	ONNX	w8a16	Qualcomm® QCS7181	6.168 ms	147 - 147 MB	NPU
YOLOv11-Pose	ONNX	w8a8_mixed_int16	Snapdragon® 8 Gen 3 Mobile	8.556 ms	17 - 258 MB	NPU
YOLOv11-Pose	ONNX	w8a8_mixed_int16	Qualcomm® QCS8550 (Proxy)	12.112 ms	11 - 28 MB	NPU
YOLOv11-Pose	ONNX	w8a8_mixed_int16	Snapdragon® 8 Elite Mobile	6.83 ms	2 - 223 MB	NPU
YOLOv11-Pose	ONNX	w8a8_mixed_int16	Snapdragon® 8 Elite Gen 5 Mobile	6.51 ms	13 - 243 MB	NPU
YOLOv11-Pose	ONNX	w8a8_mixed_int16	Qualcomm® QCS9075	17.556 ms	13 - 60 MB	NPU
YOLOv11-Pose	ONNX	w8a8_mixed_int16	Qualcomm® QCS8750	6.83 ms	2 - 223 MB	NPU
YOLOv11-Pose	QNN_DLC	float	Snapdragon® X2 Elite	3.081 ms	5 - 5 MB	NPU
YOLOv11-Pose	QNN_DLC	float	Snapdragon® X Elite	5.829 ms	5 - 5 MB	NPU
YOLOv11-Pose	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	3.732 ms	0 - 228 MB	NPU
YOLOv11-Pose	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	9.466 ms	5 - 213 MB	NPU
YOLOv11-Pose	QNN_DLC	float	Qualcomm® QCS8275	15.44 ms	2 - 205 MB	NPU
YOLOv11-Pose	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	5.271 ms	5 - 6 MB	NPU
YOLOv11-Pose	QNN_DLC	float	Qualcomm® QCS8450	9.466 ms	5 - 213 MB	NPU
YOLOv11-Pose	QNN_DLC	float	Snapdragon® 8 Elite Mobile	2.784 ms	5 - 192 MB	NPU
YOLOv11-Pose	QNN_DLC	float	Qualcomm® SA7255P	15.44 ms	2 - 205 MB	NPU
YOLOv11-Pose	QNN_DLC	float	Qualcomm® SA8295P	9.689 ms	1 - 185 MB	NPU
YOLOv11-Pose	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	2.346 ms	1 - 210 MB	NPU
YOLOv11-Pose	QNN_DLC	float	Qualcomm® QCS9075	6.328 ms	5 - 13 MB	NPU
YOLOv11-Pose	QNN_DLC	float	Qualcomm® QCS8750	2.784 ms	5 - 192 MB	NPU
YOLOv11-Pose	QNN_DLC	float	Qualcomm® QCS7181	5.829 ms	5 - 5 MB	NPU
YOLOv11-Pose	QNN_DLC	w8a16	Snapdragon® X2 Elite	2.385 ms	2 - 2 MB	NPU
YOLOv11-Pose	QNN_DLC	w8a16	Snapdragon® X Elite	5.153 ms	2 - 2 MB	NPU
YOLOv11-Pose	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	3.057 ms	2 - 209 MB	NPU
YOLOv11-Pose	QNN_DLC	w8a16	Qualcomm® QCS8275	8.806 ms	2 - 183 MB	NPU
YOLOv11-Pose	QNN_DLC	w8a16	Qualcomm® QCS8550 (Proxy)	4.673 ms	2 - 4 MB	NPU
YOLOv11-Pose	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	1.972 ms	2 - 198 MB	NPU
YOLOv11-Pose	QNN_DLC	w8a16	Snapdragon® 8 Elite Mobile	2.238 ms	2 - 187 MB	NPU
YOLOv11-Pose	QNN_DLC	w8a16	Qualcomm® QCS9075	5.312 ms	2 - 7 MB	NPU
YOLOv11-Pose	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	5.072 ms	2 - 186 MB	NPU
YOLOv11-Pose	QNN_DLC	w8a16	Qualcomm® QCM6690	21.539 ms	2 - 188 MB	NPU
YOLOv11-Pose	QNN_DLC	w8a16	Qualcomm® SA7255P	8.806 ms	2 - 183 MB	NPU
YOLOv11-Pose	QNN_DLC	w8a16	Qualcomm® QCS7790	5.072 ms	2 - 186 MB	NPU
YOLOv11-Pose	QNN_DLC	w8a16	Qualcomm® QCS8750	2.238 ms	2 - 187 MB	NPU
YOLOv11-Pose	QNN_DLC	w8a16	Qualcomm® QCS7181	5.153 ms	2 - 2 MB	NPU
YOLOv11-Pose	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	3.578 ms	1 - 140 MB	NPU
YOLOv11-Pose	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	9.381 ms	2 - 106 MB	NPU
YOLOv11-Pose	TFLITE	float	Qualcomm® QCS8275	15.33 ms	2 - 114 MB	NPU
YOLOv11-Pose	TFLITE	float	Qualcomm® QCS8550 (Proxy)	5.068 ms	2 - 4 MB	NPU
YOLOv11-Pose	TFLITE	float	Qualcomm® SA8775P	23.907 ms	0 - 31 MB	GPU
YOLOv11-Pose	TFLITE	float	Qualcomm® SA8650P	23.907 ms	0 - 31 MB	GPU
YOLOv11-Pose	TFLITE	float	Qualcomm® SA8255P	23.907 ms	0 - 31 MB	GPU
YOLOv11-Pose	TFLITE	float	Qualcomm® QCS8450	9.381 ms	2 - 106 MB	NPU
YOLOv11-Pose	TFLITE	float	Snapdragon® 8 Elite Mobile	2.615 ms	0 - 102 MB	NPU
YOLOv11-Pose	TFLITE	float	Qualcomm® SA7255P	15.33 ms	2 - 114 MB	NPU
YOLOv11-Pose	TFLITE	float	Qualcomm® SA8295P	9.43 ms	2 - 73 MB	NPU
YOLOv11-Pose	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	2.112 ms	0 - 117 MB	NPU
YOLOv11-Pose	TFLITE	float	Qualcomm® QCS9075	6.553 ms	2 - 17 MB	NPU
YOLOv11-Pose	TFLITE	float	Qualcomm® QCS8750	2.615 ms	0 - 102 MB	NPU

License

• The license for the original implementation of YOLOv11-Pose can be found here.

References

• Ultralytics YOLOv11 Docs: Pose Estimation
• 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.