YOLOv10-Detection: Optimized for Qualcomm Devices

Ultralytics YOLOv10 is a machine learning model that predicts bounding boxes and classes of objects in an image.

This is based on the implementation of YOLOv10-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

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 YOLOv10-Detection on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.object_detection

Model Stats:

• Model checkpoint: YOLOv10-N
• Input resolution: 640x640
• Number of parameters: 2.33M
• Model size (float): 8.95 MB
• Model size (w8a8): 2.55 MB
• Model size (w8a16): 3.04 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
YOLOv10-Detection	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	2.93 ms	0 - 210 MB	NPU
YOLOv10-Detection	ONNX	float	Snapdragon® 8 Elite Mobile	4.392 ms	0 - 203 MB	NPU
YOLOv10-Detection	ONNX	float	Snapdragon® X2 Elite	3.253 ms	3 - 3 MB	NPU
YOLOv10-Detection	ONNX	float	Snapdragon® X Elite	6.854 ms	5 - 5 MB	NPU
YOLOv10-Detection	ONNX	float	Snapdragon® X Elite	6.854 ms	5 - 5 MB	NPU
YOLOv10-Detection	ONNX	float	Snapdragon® 8 Gen 3 Mobile	3.937 ms	1 - 242 MB	NPU
YOLOv10-Detection	ONNX	float	Qualcomm® QCS8550 (Proxy)	6.311 ms	5 - 10 MB	NPU
YOLOv10-Detection	ONNX	float	Qualcomm® QCS9075	7.055 ms	5 - 7 MB	NPU
YOLOv10-Detection	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	4.392 ms	0 - 203 MB	NPU
YOLOv10-Detection	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	2.271 ms	0 - 79 MB	NPU
YOLOv10-Detection	ONNX	w8a16	Snapdragon® 8 Elite Mobile	2.526 ms	1 - 79 MB	NPU
YOLOv10-Detection	ONNX	w8a16	Snapdragon® X2 Elite	2.435 ms	0 - 0 MB	NPU
YOLOv10-Detection	ONNX	w8a16	Snapdragon® X Elite	5.827 ms	2 - 2 MB	NPU
YOLOv10-Detection	ONNX	w8a16	Snapdragon® X Elite	5.827 ms	2 - 2 MB	NPU
YOLOv10-Detection	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	3.343 ms	3 - 106 MB	NPU
YOLOv10-Detection	ONNX	w8a16	Qualcomm® QCS6490	326.781 ms	70 - 75 MB	CPU
YOLOv10-Detection	ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	5.376 ms	2 - 7 MB	NPU
YOLOv10-Detection	ONNX	w8a16	Qualcomm® QCS9075	6.656 ms	2 - 5 MB	NPU
YOLOv10-Detection	ONNX	w8a16	Qualcomm® QCM6690	168.686 ms	58 - 67 MB	CPU
YOLOv10-Detection	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	2.526 ms	1 - 79 MB	NPU
YOLOv10-Detection	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	149.786 ms	73 - 83 MB	CPU
YOLOv10-Detection	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	149.786 ms	73 - 83 MB	CPU
YOLOv10-Detection	ONNX	w8a8_mixed_int16	Snapdragon® 8 Elite Gen 5 Mobile	5.943 ms	8 - 225 MB	NPU
YOLOv10-Detection	ONNX	w8a8_mixed_int16	Snapdragon® 8 Elite Mobile	6.295 ms	6 - 217 MB	NPU
YOLOv10-Detection	ONNX	w8a8_mixed_int16	Snapdragon® X2 Elite	6.382 ms	10 - 10 MB	NPU
YOLOv10-Detection	ONNX	w8a8_mixed_int16	Snapdragon® X Elite	15.045 ms	8 - 8 MB	NPU
YOLOv10-Detection	ONNX	w8a8_mixed_int16	Snapdragon® X Elite	15.045 ms	8 - 8 MB	NPU
YOLOv10-Detection	ONNX	w8a8_mixed_int16	Snapdragon® 8 Gen 3 Mobile	8.341 ms	8 - 338 MB	NPU
YOLOv10-Detection	ONNX	w8a8_mixed_int16	Qualcomm® QCS6490	137.225 ms	58 - 69 MB	CPU
YOLOv10-Detection	ONNX	w8a8_mixed_int16	Qualcomm® QCS8550 (Proxy)	11.799 ms	7 - 13 MB	NPU
YOLOv10-Detection	ONNX	w8a8_mixed_int16	Qualcomm® QCS9075	15.521 ms	7 - 10 MB	NPU
YOLOv10-Detection	ONNX	w8a8_mixed_int16	Qualcomm® QCM6690	79.439 ms	51 - 63 MB	CPU
YOLOv10-Detection	ONNX	w8a8_mixed_int16	Snapdragon® 8 Elite For Galaxy Mobile	6.295 ms	6 - 217 MB	NPU
YOLOv10-Detection	ONNX	w8a8_mixed_int16	Snapdragon® 7 Gen 4 Mobile	70.776 ms	65 - 77 MB	CPU
YOLOv10-Detection	ONNX	w8a8_mixed_int16	Snapdragon® 7 Gen 4 Mobile	70.776 ms	65 - 77 MB	CPU
YOLOv10-Detection	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	1.939 ms	5 - 198 MB	NPU
YOLOv10-Detection	QNN_DLC	float	Snapdragon® 8 Elite Mobile	2.279 ms	0 - 181 MB	NPU
YOLOv10-Detection	QNN_DLC	float	Snapdragon® X2 Elite	2.691 ms	5 - 5 MB	NPU
YOLOv10-Detection	QNN_DLC	float	Snapdragon® X Elite	4.546 ms	5 - 5 MB	NPU
YOLOv10-Detection	QNN_DLC	float	Snapdragon® X Elite	4.546 ms	5 - 5 MB	NPU
YOLOv10-Detection	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	3.038 ms	5 - 215 MB	NPU
YOLOv10-Detection	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	13.343 ms	1 - 182 MB	NPU
YOLOv10-Detection	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	4.167 ms	5 - 10 MB	NPU
YOLOv10-Detection	QNN_DLC	float	Qualcomm® SA8775P	5.582 ms	1 - 188 MB	NPU
YOLOv10-Detection	QNN_DLC	float	Qualcomm® SA8775P	5.582 ms	1 - 188 MB	NPU
YOLOv10-Detection	QNN_DLC	float	Qualcomm® SA8775P	5.582 ms	1 - 188 MB	NPU
YOLOv10-Detection	QNN_DLC	float	Qualcomm® QCS9075	5.194 ms	5 - 11 MB	NPU
YOLOv10-Detection	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	8.516 ms	4 - 201 MB	NPU
YOLOv10-Detection	QNN_DLC	float	Qualcomm® SA7255P	13.343 ms	1 - 182 MB	NPU
YOLOv10-Detection	QNN_DLC	float	Qualcomm® SA8295P	8.903 ms	0 - 170 MB	NPU
YOLOv10-Detection	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	2.279 ms	0 - 181 MB	NPU
YOLOv10-Detection	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	1.733 ms	1 - 183 MB	NPU
YOLOv10-Detection	QNN_DLC	w8a16	Snapdragon® 8 Elite Mobile	2.021 ms	2 - 178 MB	NPU
YOLOv10-Detection	QNN_DLC	w8a16	Snapdragon® X2 Elite	2.302 ms	2 - 2 MB	NPU
YOLOv10-Detection	QNN_DLC	w8a16	Snapdragon® X Elite	4.624 ms	2 - 2 MB	NPU
YOLOv10-Detection	QNN_DLC	w8a16	Snapdragon® X Elite	4.624 ms	2 - 2 MB	NPU
YOLOv10-Detection	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	2.899 ms	2 - 198 MB	NPU
YOLOv10-Detection	QNN_DLC	w8a16	Qualcomm® QCS8275 (Proxy)	7.937 ms	1 - 174 MB	NPU
YOLOv10-Detection	QNN_DLC	w8a16	Qualcomm® QCS8550 (Proxy)	4.263 ms	0 - 5 MB	NPU
YOLOv10-Detection	QNN_DLC	w8a16	Qualcomm® SA8775P	4.821 ms	1 - 178 MB	NPU
YOLOv10-Detection	QNN_DLC	w8a16	Qualcomm® SA8775P	4.821 ms	1 - 178 MB	NPU
YOLOv10-Detection	QNN_DLC	w8a16	Qualcomm® SA8775P	4.821 ms	1 - 178 MB	NPU
YOLOv10-Detection	QNN_DLC	w8a16	Qualcomm® QCS9075	4.766 ms	0 - 4 MB	NPU
YOLOv10-Detection	QNN_DLC	w8a16	Qualcomm® QCM6690	19.932 ms	2 - 180 MB	NPU
YOLOv10-Detection	QNN_DLC	w8a16	Qualcomm® SA7255P	7.937 ms	1 - 174 MB	NPU
YOLOv10-Detection	QNN_DLC	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	2.021 ms	2 - 178 MB	NPU
YOLOv10-Detection	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	4.489 ms	2 - 180 MB	NPU
YOLOv10-Detection	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	4.489 ms	2 - 180 MB	NPU
YOLOv10-Detection	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	1.641 ms	0 - 89 MB	NPU
YOLOv10-Detection	TFLITE	float	Snapdragon® 8 Elite Mobile	2.043 ms	0 - 78 MB	NPU
YOLOv10-Detection	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	2.685 ms	0 - 109 MB	NPU
YOLOv10-Detection	TFLITE	float	Qualcomm® QCS8275 (Proxy)	12.777 ms	0 - 79 MB	NPU
YOLOv10-Detection	TFLITE	float	Qualcomm® QCS8550 (Proxy)	3.776 ms	0 - 5 MB	NPU
YOLOv10-Detection	TFLITE	float	Qualcomm® SA8775P	5.221 ms	0 - 83 MB	NPU
YOLOv10-Detection	TFLITE	float	Qualcomm® SA8775P	5.221 ms	0 - 83 MB	NPU
YOLOv10-Detection	TFLITE	float	Qualcomm® SA8775P	5.221 ms	0 - 83 MB	NPU
YOLOv10-Detection	TFLITE	float	Qualcomm® QCS9075	4.927 ms	0 - 13 MB	NPU
YOLOv10-Detection	TFLITE	float	Qualcomm® QCS8450 (Proxy)	7.401 ms	0 - 80 MB	NPU
YOLOv10-Detection	TFLITE	float	Qualcomm® SA7255P	12.777 ms	0 - 79 MB	NPU
YOLOv10-Detection	TFLITE	float	Qualcomm® SA8295P	8.246 ms	0 - 56 MB	NPU
YOLOv10-Detection	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	2.043 ms	0 - 78 MB	NPU

License

• The license for the original implementation of YOLOv10-Detection can be found here.

References

• YOLOv10: Real-Time End-to-End Object Detection
• 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.