Depth-Anything-V2: 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-V2 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-V2 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-V2 on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.depth_estimation

Model Stats:

• Model checkpoint: DepthAnything_V2_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-V2	ONNX	float	Snapdragon® X2 Elite	34.613 ms	51 - 51 MB	NPU
Depth-Anything-V2	ONNX	float	Snapdragon® X Elite	79.587 ms	50 - 50 MB	NPU
Depth-Anything-V2	ONNX	float	Snapdragon® 8 Gen 3 Mobile	54.907 ms	0 - 849 MB	NPU
Depth-Anything-V2	ONNX	float	Qualcomm® QCS8550 (Proxy)	76.098 ms	0 - 68 MB	NPU
Depth-Anything-V2	ONNX	float	Qualcomm® QCS9075	98.824 ms	3 - 9 MB	NPU
Depth-Anything-V2	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	41.513 ms	2 - 586 MB	NPU
Depth-Anything-V2	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	34.633 ms	5 - 660 MB	NPU
Depth-Anything-V2	QNN_DLC	float	Snapdragon® X2 Elite	34.633 ms	3 - 3 MB	NPU
Depth-Anything-V2	QNN_DLC	float	Snapdragon® X Elite	76.4 ms	3 - 3 MB	NPU
Depth-Anything-V2	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	54.928 ms	3 - 669 MB	NPU
Depth-Anything-V2	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	176.687 ms	1 - 486 MB	NPU
Depth-Anything-V2	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	74.543 ms	3 - 6 MB	NPU
Depth-Anything-V2	QNN_DLC	float	Qualcomm® SA8775P	80.991 ms	1 - 496 MB	NPU
Depth-Anything-V2	QNN_DLC	float	Qualcomm® QCS9075	96.558 ms	3 - 9 MB	NPU
Depth-Anything-V2	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	115.581 ms	1 - 602 MB	NPU
Depth-Anything-V2	QNN_DLC	float	Qualcomm® SA7255P	176.687 ms	1 - 486 MB	NPU
Depth-Anything-V2	QNN_DLC	float	Qualcomm® SA8295P	106.129 ms	0 - 484 MB	NPU
Depth-Anything-V2	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	40.517 ms	1 - 493 MB	NPU
Depth-Anything-V2	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	36.034 ms	2 - 503 MB	NPU
Depth-Anything-V2	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	50.806 ms	0 - 589 MB	NPU
Depth-Anything-V2	TFLITE	float	Qualcomm® QCS8275 (Proxy)	173.857 ms	1 - 444 MB	NPU
Depth-Anything-V2	TFLITE	float	Qualcomm® QCS8550 (Proxy)	72.541 ms	1 - 8 MB	NPU
Depth-Anything-V2	TFLITE	float	Qualcomm® SA8775P	377.558 ms	1 - 445 MB	NPU
Depth-Anything-V2	TFLITE	float	Qualcomm® QCS9075	89.524 ms	1 - 58 MB	NPU
Depth-Anything-V2	TFLITE	float	Qualcomm® QCS8450 (Proxy)	105.077 ms	1 - 585 MB	NPU
Depth-Anything-V2	TFLITE	float	Qualcomm® SA7255P	173.857 ms	1 - 444 MB	NPU
Depth-Anything-V2	TFLITE	float	Qualcomm® SA8295P	100.216 ms	1 - 471 MB	NPU
Depth-Anything-V2	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	35.628 ms	1 - 459 MB	NPU
Depth-Anything-V2	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	31.521 ms	1 - 466 MB	NPU

License

• The license for the original implementation of Depth-Anything-V2 can be found here.

References

• Depth Anything V2
• 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.