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	2.721 ms	1 - 220 MB	NPU
YOLOv10-Detection	ONNX	float	Snapdragon® X2 Elite	3.092 ms	3 - 3 MB	NPU
YOLOv10-Detection	ONNX	float	Snapdragon® X Elite	6.69 ms	5 - 5 MB	NPU
YOLOv10-Detection	ONNX	float	Snapdragon® 8 Gen 3 Mobile	3.834 ms	2 - 275 MB	NPU
YOLOv10-Detection	ONNX	float	Qualcomm® QCS8550 (Proxy)	6.129 ms	5 - 11 MB	NPU
YOLOv10-Detection	ONNX	float	Qualcomm® QCS9075	7.015 ms	5 - 7 MB	NPU
YOLOv10-Detection	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	3.056 ms	1 - 224 MB	NPU
YOLOv10-Detection	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	2.074 ms	0 - 79 MB	NPU
YOLOv10-Detection	ONNX	w8a16	Snapdragon® X2 Elite	2.242 ms	0 - 0 MB	NPU
YOLOv10-Detection	ONNX	w8a16	Snapdragon® X Elite	5.548 ms	2 - 2 MB	NPU
YOLOv10-Detection	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	3.158 ms	0 - 105 MB	NPU
YOLOv10-Detection	ONNX	w8a16	Qualcomm® QCS6490	328.145 ms	66 - 71 MB	CPU
YOLOv10-Detection	ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	5.068 ms	2 - 7 MB	NPU
YOLOv10-Detection	ONNX	w8a16	Qualcomm® QCS9075	6.097 ms	2 - 5 MB	NPU
YOLOv10-Detection	ONNX	w8a16	Qualcomm® QCM6690	168.745 ms	58 - 67 MB	CPU
YOLOv10-Detection	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	2.297 ms	0 - 72 MB	NPU
YOLOv10-Detection	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	149.11 ms	68 - 77 MB	CPU
YOLOv10-Detection	ONNX	w8a8_mixed_int16	Snapdragon® 8 Elite Gen 5 Mobile	6.353 ms	9 - 323 MB	NPU
YOLOv10-Detection	ONNX	w8a8_mixed_int16	Snapdragon® X2 Elite	6.739 ms	10 - 10 MB	NPU
YOLOv10-Detection	ONNX	w8a8_mixed_int16	Snapdragon® X Elite	14.143 ms	8 - 8 MB	NPU
YOLOv10-Detection	ONNX	w8a8_mixed_int16	Snapdragon® 8 Gen 3 Mobile	8.525 ms	9 - 242 MB	NPU
YOLOv10-Detection	ONNX	w8a8_mixed_int16	Qualcomm® QCS6490	142.78 ms	60 - 71 MB	CPU
YOLOv10-Detection	ONNX	w8a8_mixed_int16	Qualcomm® QCS8550 (Proxy)	11.826 ms	7 - 12 MB	NPU
YOLOv10-Detection	ONNX	w8a8_mixed_int16	Qualcomm® QCS9075	16.348 ms	7 - 10 MB	NPU
YOLOv10-Detection	ONNX	w8a8_mixed_int16	Qualcomm® QCM6690	81.311 ms	63 - 74 MB	CPU
YOLOv10-Detection	ONNX	w8a8_mixed_int16	Snapdragon® 8 Elite For Galaxy Mobile	6.446 ms	6 - 193 MB	NPU
YOLOv10-Detection	ONNX	w8a8_mixed_int16	Snapdragon® 7 Gen 4 Mobile	71.621 ms	62 - 73 MB	CPU
YOLOv10-Detection	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	1.875 ms	3 - 190 MB	NPU
YOLOv10-Detection	QNN_DLC	float	Snapdragon® X2 Elite	2.54 ms	5 - 5 MB	NPU
YOLOv10-Detection	QNN_DLC	float	Snapdragon® X Elite	4.383 ms	5 - 5 MB	NPU
YOLOv10-Detection	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	2.951 ms	0 - 210 MB	NPU
YOLOv10-Detection	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	13.092 ms	1 - 183 MB	NPU
YOLOv10-Detection	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	3.96 ms	5 - 103 MB	NPU
YOLOv10-Detection	QNN_DLC	float	Qualcomm® SA8775P	5.425 ms	0 - 183 MB	NPU
YOLOv10-Detection	QNN_DLC	float	Qualcomm® QCS9075	5.105 ms	5 - 11 MB	NPU
YOLOv10-Detection	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	9.151 ms	4 - 197 MB	NPU
YOLOv10-Detection	QNN_DLC	float	Qualcomm® SA7255P	13.092 ms	1 - 183 MB	NPU
YOLOv10-Detection	QNN_DLC	float	Qualcomm® SA8295P	8.883 ms	0 - 167 MB	NPU
YOLOv10-Detection	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	2.203 ms	5 - 186 MB	NPU
YOLOv10-Detection	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	1.8 ms	2 - 183 MB	NPU
YOLOv10-Detection	QNN_DLC	w8a16	Snapdragon® X2 Elite	2.194 ms	2 - 2 MB	NPU
YOLOv10-Detection	QNN_DLC	w8a16	Snapdragon® X Elite	4.678 ms	2 - 2 MB	NPU
YOLOv10-Detection	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	3.006 ms	0 - 199 MB	NPU
YOLOv10-Detection	QNN_DLC	w8a16	Qualcomm® QCS8275 (Proxy)	8.172 ms	0 - 173 MB	NPU
YOLOv10-Detection	QNN_DLC	w8a16	Qualcomm® QCS8550 (Proxy)	4.299 ms	2 - 4 MB	NPU
YOLOv10-Detection	QNN_DLC	w8a16	Qualcomm® SA8775P	4.92 ms	1 - 176 MB	NPU
YOLOv10-Detection	QNN_DLC	w8a16	Qualcomm® QCS9075	4.826 ms	0 - 4 MB	NPU
YOLOv10-Detection	QNN_DLC	w8a16	Qualcomm® QCM6690	19.461 ms	2 - 183 MB	NPU
YOLOv10-Detection	QNN_DLC	w8a16	Qualcomm® SA7255P	8.172 ms	0 - 173 MB	NPU
YOLOv10-Detection	QNN_DLC	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	2.123 ms	2 - 178 MB	NPU
YOLOv10-Detection	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	4.532 ms	2 - 177 MB	NPU
YOLOv10-Detection	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	1.582 ms	0 - 91 MB	NPU
YOLOv10-Detection	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	2.647 ms	0 - 114 MB	NPU
YOLOv10-Detection	TFLITE	float	Qualcomm® QCS8275 (Proxy)	12.567 ms	0 - 81 MB	NPU
YOLOv10-Detection	TFLITE	float	Qualcomm® QCS8550 (Proxy)	3.58 ms	0 - 2 MB	NPU
YOLOv10-Detection	TFLITE	float	Qualcomm® SA8775P	20.919 ms	0 - 83 MB	NPU
YOLOv10-Detection	TFLITE	float	Qualcomm® QCS9075	4.828 ms	0 - 13 MB	NPU
YOLOv10-Detection	TFLITE	float	Qualcomm® QCS8450 (Proxy)	7.759 ms	0 - 196 MB	NPU
YOLOv10-Detection	TFLITE	float	Qualcomm® SA7255P	12.567 ms	0 - 81 MB	NPU
YOLOv10-Detection	TFLITE	float	Qualcomm® SA8295P	8.154 ms	0 - 170 MB	NPU
YOLOv10-Detection	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	1.982 ms	0 - 94 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.