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® X2 Elite	3.353 ms	208 - 208 MB	NPU
YOLOv10-Detection	ONNX	float	Snapdragon® X Elite	6.691 ms	177 - 177 MB	NPU
YOLOv10-Detection	ONNX	float	Snapdragon® 8 Gen 3 Mobile	3.917 ms	0 - 228 MB	NPU
YOLOv10-Detection	ONNX	float	Snapdragon® 8 Gen 1 Mobile	14.926 ms	5 - 203 MB	NPU
YOLOv10-Detection	ONNX	float	Qualcomm® QCS8550 (Proxy)	6.373 ms	5 - 13 MB	NPU
YOLOv10-Detection	ONNX	float	Qualcomm® QCS8450	14.926 ms	5 - 203 MB	NPU
YOLOv10-Detection	ONNX	float	Snapdragon® 8 Elite Mobile	4.403 ms	0 - 198 MB	NPU
YOLOv10-Detection	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	2.993 ms	0 - 215 MB	NPU
YOLOv10-Detection	ONNX	float	Qualcomm® QCS9075	7.434 ms	3 - 50 MB	NPU
YOLOv10-Detection	ONNX	float	Qualcomm® QCS8750	4.403 ms	0 - 198 MB	NPU
YOLOv10-Detection	ONNX	float	Qualcomm® QCS7181	6.691 ms	177 - 177 MB	NPU
YOLOv10-Detection	ONNX	w8a16	Snapdragon® X2 Elite	2.43 ms	210 - 210 MB	NPU
YOLOv10-Detection	ONNX	w8a16	Snapdragon® X Elite	5.702 ms	148 - 148 MB	NPU
YOLOv10-Detection	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	3.354 ms	4 - 94 MB	NPU
YOLOv10-Detection	ONNX	w8a16	Snapdragon® 8 Gen 1 Mobile	6.705 ms	3 - 89 MB	NPU
YOLOv10-Detection	ONNX	w8a16	Qualcomm® QCS6490	13.256 ms	1 - 48 MB	NPU
YOLOv10-Detection	ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	5.371 ms	2 - 11 MB	NPU
YOLOv10-Detection	ONNX	w8a16	Qualcomm® QCS8450	6.705 ms	3 - 89 MB	NPU
YOLOv10-Detection	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	2.283 ms	1 - 81 MB	NPU
YOLOv10-Detection	ONNX	w8a16	Snapdragon® 8 Elite Mobile	2.518 ms	2 - 80 MB	NPU
YOLOv10-Detection	ONNX	w8a16	Qualcomm® QCS9075	6.714 ms	2 - 48 MB	NPU
YOLOv10-Detection	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	6.617 ms	2 - 192 MB	NPU
YOLOv10-Detection	ONNX	w8a16	Qualcomm® QCM6690	24.85 ms	2 - 192 MB	NPU
YOLOv10-Detection	ONNX	w8a16	Qualcomm® QCS7790	6.617 ms	2 - 192 MB	NPU
YOLOv10-Detection	ONNX	w8a16	Qualcomm® QCS8750	2.518 ms	2 - 80 MB	NPU
YOLOv10-Detection	ONNX	w8a16	Qualcomm® QCS7181	5.702 ms	148 - 148 MB	NPU
YOLOv10-Detection	ONNX	w8a8_mixed_int16	Snapdragon® 8 Gen 3 Mobile	7.576 ms	8 - 331 MB	NPU
YOLOv10-Detection	ONNX	w8a8_mixed_int16	Qualcomm® QCS8550 (Proxy)	10.634 ms	5 - 17 MB	NPU
YOLOv10-Detection	ONNX	w8a8_mixed_int16	Snapdragon® 8 Elite Mobile	5.813 ms	0 - 307 MB	NPU
YOLOv10-Detection	ONNX	w8a8_mixed_int16	Snapdragon® 8 Elite Gen 5 Mobile	5.897 ms	6 - 318 MB	NPU
YOLOv10-Detection	ONNX	w8a8_mixed_int16	Qualcomm® QCS9075	15.151 ms	5 - 51 MB	NPU
YOLOv10-Detection	ONNX	w8a8_mixed_int16	Qualcomm® QCS8750	5.813 ms	0 - 307 MB	NPU
YOLOv10-Detection	QNN_DLC	float	Snapdragon® X2 Elite	5.835 ms	5 - 5 MB	NPU
YOLOv10-Detection	QNN_DLC	float	Snapdragon® X Elite	4.705 ms	5 - 5 MB	NPU
YOLOv10-Detection	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	3.046 ms	0 - 212 MB	NPU
YOLOv10-Detection	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	8.559 ms	3 - 200 MB	NPU
YOLOv10-Detection	QNN_DLC	float	Qualcomm® QCS8275	13.279 ms	0 - 182 MB	NPU
YOLOv10-Detection	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	4.138 ms	3 - 6 MB	NPU
YOLOv10-Detection	QNN_DLC	float	Qualcomm® QCS8450	8.559 ms	3 - 200 MB	NPU
YOLOv10-Detection	QNN_DLC	float	Snapdragon® 8 Elite Mobile	2.276 ms	0 - 188 MB	NPU
YOLOv10-Detection	QNN_DLC	float	Qualcomm® SA7255P	13.279 ms	0 - 182 MB	NPU
YOLOv10-Detection	QNN_DLC	float	Qualcomm® SA8295P	8.905 ms	0 - 170 MB	NPU
YOLOv10-Detection	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	1.95 ms	5 - 198 MB	NPU
YOLOv10-Detection	QNN_DLC	float	Qualcomm® QCS9075	5.192 ms	5 - 11 MB	NPU
YOLOv10-Detection	QNN_DLC	float	Qualcomm® QCS8750	2.276 ms	0 - 188 MB	NPU
YOLOv10-Detection	QNN_DLC	float	Qualcomm® QCS7181	4.705 ms	5 - 5 MB	NPU
YOLOv10-Detection	QNN_DLC	w8a16	Snapdragon® X2 Elite	3.298 ms	2 - 2 MB	NPU
YOLOv10-Detection	QNN_DLC	w8a16	Snapdragon® X Elite	4.645 ms	2 - 2 MB	NPU
YOLOv10-Detection	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	2.912 ms	2 - 198 MB	NPU
YOLOv10-Detection	QNN_DLC	w8a16	Qualcomm® QCS8275	7.936 ms	1 - 175 MB	NPU
YOLOv10-Detection	QNN_DLC	w8a16	Qualcomm® QCS8550 (Proxy)	4.228 ms	2 - 4 MB	NPU
YOLOv10-Detection	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	1.748 ms	2 - 187 MB	NPU
YOLOv10-Detection	QNN_DLC	w8a16	Snapdragon® 8 Elite Mobile	2.018 ms	2 - 180 MB	NPU
YOLOv10-Detection	QNN_DLC	w8a16	Qualcomm® QCS9075	4.772 ms	3 - 7 MB	NPU
YOLOv10-Detection	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	4.459 ms	2 - 177 MB	NPU
YOLOv10-Detection	QNN_DLC	w8a16	Qualcomm® QCM6690	20.072 ms	2 - 180 MB	NPU
YOLOv10-Detection	QNN_DLC	w8a16	Qualcomm® SA7255P	7.936 ms	1 - 175 MB	NPU
YOLOv10-Detection	QNN_DLC	w8a16	Qualcomm® QCS7790	4.459 ms	2 - 177 MB	NPU
YOLOv10-Detection	QNN_DLC	w8a16	Qualcomm® QCS8750	2.018 ms	2 - 180 MB	NPU
YOLOv10-Detection	QNN_DLC	w8a16	Qualcomm® QCS7181	4.645 ms	2 - 2 MB	NPU
YOLOv10-Detection	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	2.683 ms	0 - 105 MB	NPU
YOLOv10-Detection	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	7.478 ms	0 - 84 MB	NPU
YOLOv10-Detection	TFLITE	float	Qualcomm® QCS8275	12.747 ms	0 - 79 MB	NPU
YOLOv10-Detection	TFLITE	float	Qualcomm® QCS8550 (Proxy)	3.759 ms	0 - 2 MB	NPU
YOLOv10-Detection	TFLITE	float	Qualcomm® SA8775P	19.399 ms	2 - 34 MB	GPU
YOLOv10-Detection	TFLITE	float	Qualcomm® SA8650P	19.399 ms	2 - 34 MB	GPU
YOLOv10-Detection	TFLITE	float	Qualcomm® SA8255P	19.399 ms	2 - 34 MB	GPU
YOLOv10-Detection	TFLITE	float	Qualcomm® QCS8450	7.478 ms	0 - 84 MB	NPU
YOLOv10-Detection	TFLITE	float	Snapdragon® 8 Elite Mobile	2.05 ms	0 - 88 MB	NPU
YOLOv10-Detection	TFLITE	float	Qualcomm® SA7255P	12.747 ms	0 - 79 MB	NPU
YOLOv10-Detection	TFLITE	float	Qualcomm® SA8295P	8.25 ms	0 - 56 MB	NPU
YOLOv10-Detection	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	1.651 ms	0 - 82 MB	NPU
YOLOv10-Detection	TFLITE	float	Qualcomm® QCS9075	4.911 ms	0 - 13 MB	NPU
YOLOv10-Detection	TFLITE	float	Qualcomm® QCS8750	2.05 ms	0 - 88 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.