Depth-Anything: Optimized for Qualcomm Devices

Depth Anything is designed for estimating depth at each point in an image.

This is based on the implementation of Depth-Anything 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 2.42, ONNX Runtime 1.24.1	Download
ONNX	w8a16	Universal	QAIRT 2.42, ONNX Runtime 1.24.1	Download
QNN_DLC	float	Universal	QAIRT 2.43	Download
QNN_DLC	w8a16	Universal	QAIRT 2.43	Download
TFLITE	float	Universal	QAIRT 2.43, TFLite 2.17.0	Download

For more device-specific assets and performance metrics, visit Depth-Anything 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 Depth-Anything on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.depth_estimation

Model Stats:

• Model checkpoint: DepthAnything_Small
• Input resolution: 518x518
• Number of parameters: 24.7M
• Model size (float): 94.3 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
Depth-Anything	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	34.956 ms	5 - 663 MB	NPU
Depth-Anything	ONNX	float	Snapdragon® X2 Elite	34.486 ms	51 - 51 MB	NPU
Depth-Anything	ONNX	float	Snapdragon® X Elite	79.348 ms	50 - 50 MB	NPU
Depth-Anything	ONNX	float	Snapdragon® 8 Gen 3 Mobile	55.548 ms	0 - 852 MB	NPU
Depth-Anything	ONNX	float	Qualcomm® QCS8550 (Proxy)	75.974 ms	0 - 55 MB	NPU
Depth-Anything	ONNX	float	Qualcomm® QCS9075	98.569 ms	3 - 9 MB	NPU
Depth-Anything	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	41.337 ms	2 - 657 MB	NPU
Depth-Anything	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	27.119 ms	3 - 575 MB	NPU
Depth-Anything	ONNX	w8a16	Snapdragon® X2 Elite	26.248 ms	30 - 30 MB	NPU
Depth-Anything	ONNX	w8a16	Snapdragon® X Elite	54.935 ms	29 - 29 MB	NPU
Depth-Anything	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	40.72 ms	3 - 1050 MB	NPU
Depth-Anything	ONNX	w8a16	Qualcomm® QCS6490	3239.547 ms	159 - 164 MB	CPU
Depth-Anything	ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	55.867 ms	0 - 725 MB	NPU
Depth-Anything	ONNX	w8a16	Qualcomm® QCS9075	79.176 ms	2 - 5 MB	NPU
Depth-Anything	ONNX	w8a16	Qualcomm® QCM6690	1687.184 ms	160 - 175 MB	CPU
Depth-Anything	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	32.243 ms	3 - 837 MB	NPU
Depth-Anything	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	1621.137 ms	160 - 177 MB	CPU
Depth-Anything	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	36.061 ms	3 - 505 MB	NPU
Depth-Anything	QNN_DLC	float	Snapdragon® X2 Elite	34.659 ms	3 - 3 MB	NPU
Depth-Anything	QNN_DLC	float	Snapdragon® X Elite	76.291 ms	3 - 3 MB	NPU
Depth-Anything	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	54.577 ms	3 - 663 MB	NPU
Depth-Anything	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	176.103 ms	0 - 491 MB	NPU
Depth-Anything	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	74.855 ms	3 - 5 MB	NPU
Depth-Anything	QNN_DLC	float	Qualcomm® SA8775P	80.684 ms	1 - 496 MB	NPU
Depth-Anything	QNN_DLC	float	Qualcomm® QCS9075	96.443 ms	3 - 9 MB	NPU
Depth-Anything	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	118.134 ms	0 - 608 MB	NPU
Depth-Anything	QNN_DLC	float	Qualcomm® SA7255P	176.103 ms	0 - 491 MB	NPU
Depth-Anything	QNN_DLC	float	Qualcomm® SA8295P	104.536 ms	0 - 520 MB	NPU
Depth-Anything	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	40.791 ms	2 - 496 MB	NPU
Depth-Anything	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	31.464 ms	1 - 465 MB	NPU
Depth-Anything	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	50.445 ms	0 - 595 MB	NPU
Depth-Anything	TFLITE	float	Qualcomm® QCS8275 (Proxy)	176.503 ms	1 - 445 MB	NPU
Depth-Anything	TFLITE	float	Qualcomm® QCS8550 (Proxy)	72.401 ms	1 - 12 MB	NPU
Depth-Anything	TFLITE	float	Qualcomm® SA8775P	377.281 ms	1 - 444 MB	NPU
Depth-Anything	TFLITE	float	Qualcomm® QCS9075	89.487 ms	1 - 58 MB	NPU
Depth-Anything	TFLITE	float	Qualcomm® QCS8450 (Proxy)	105.206 ms	1 - 582 MB	NPU
Depth-Anything	TFLITE	float	Qualcomm® SA7255P	176.503 ms	1 - 445 MB	NPU
Depth-Anything	TFLITE	float	Qualcomm® SA8295P	101.06 ms	1 - 435 MB	NPU
Depth-Anything	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	37.697 ms	1 - 458 MB	NPU

License

• The license for the original implementation of Depth-Anything can be found here.

References

• Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data
• 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.