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 2.45, ONNX Runtime 1.27.1	Download
ONNX	w8a16	Universal	QAIRT 2.45, ONNX Runtime 1.27.1	Download
QNN_DLC	float	Universal	QAIRT 2.45	Download
QNN_DLC	w8a16	Universal	QAIRT 2.45	Download
TFLITE	float	Universal	QAIRT 2.45	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:

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

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
Depth-Anything	ONNX	float	Snapdragon® X2 Elite	19.086 ms	4 - 4 MB	NPU
Depth-Anything	ONNX	float	Snapdragon® X Elite	48.986 ms	47 - 47 MB	NPU
Depth-Anything	ONNX	float	Snapdragon® 8 Gen 3 Mobile	35.83 ms	0 - 471 MB	NPU
Depth-Anything	ONNX	float	Snapdragon® 8 Gen 1 Mobile	86.045 ms	1 - 477 MB	NPU
Depth-Anything	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	57.247 ms	3 - 9 MB	NPU
Depth-Anything	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	47.448 ms	0 - 56 MB	NPU
Depth-Anything	ONNX	float	Qualcomm® QCS8450	86.045 ms	1 - 477 MB	NPU
Depth-Anything	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	61.943 ms	3 - 9 MB	NPU
Depth-Anything	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	48.986 ms	47 - 47 MB	NPU
Depth-Anything	ONNX	float	Qualcomm® Dragonwing™ Q-8750	24.317 ms	2 - 367 MB	NPU
Depth-Anything	ONNX	float	Snapdragon® 8 Elite Mobile	24.317 ms	2 - 367 MB	NPU
Depth-Anything	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	18.557 ms	2 - 372 MB	NPU
Depth-Anything	ONNX	w8a16	Snapdragon® X2 Elite	12.018 ms	4 - 4 MB	NPU
Depth-Anything	ONNX	w8a16	Snapdragon® X Elite	27.753 ms	27 - 27 MB	NPU
Depth-Anything	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	18.79 ms	3 - 512 MB	NPU
Depth-Anything	ONNX	w8a16	Snapdragon® 8 Gen 1 Mobile	39.067 ms	3 - 512 MB	NPU
Depth-Anything	ONNX	w8a16	Qualcomm® Dragonwing™ QCS6490	107.453 ms	2 - 5 MB	NPU
Depth-Anything	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-8275	25.052 ms	2 - 6 MB	NPU
Depth-Anything	ONNX	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	26.922 ms	0 - 34 MB	NPU
Depth-Anything	ONNX	w8a16	Qualcomm® QCS8450	39.067 ms	3 - 512 MB	NPU
Depth-Anything	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-9075	27.579 ms	2 - 5 MB	NPU
Depth-Anything	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-X7181	27.753 ms	27 - 27 MB	NPU
Depth-Anything	ONNX	w8a16	Qualcomm® Dragonwing™ Q-6690	232.248 ms	3 - 644 MB	NPU
Depth-Anything	ONNX	w8a16	Qualcomm® Dragonwing™ Q-7790	35.771 ms	3 - 612 MB	NPU
Depth-Anything	ONNX	w8a16	Qualcomm® Dragonwing™ Q-8750	14.007 ms	3 - 421 MB	NPU
Depth-Anything	ONNX	w8a16	Snapdragon® 8 Elite Mobile	14.007 ms	3 - 421 MB	NPU
Depth-Anything	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	11.571 ms	1 - 426 MB	NPU
Depth-Anything	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	35.771 ms	3 - 612 MB	NPU
Depth-Anything	QNN_DLC	float	Snapdragon® X2 Elite	20.263 ms	3 - 3 MB	NPU
Depth-Anything	QNN_DLC	float	Snapdragon® X Elite	51.394 ms	3 - 3 MB	NPU
Depth-Anything	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	39.36 ms	0 - 510 MB	NPU
Depth-Anything	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	92.553 ms	3 - 485 MB	NPU
Depth-Anything	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	57.472 ms	3 - 10 MB	NPU
Depth-Anything	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	142.179 ms	2 - 389 MB	NPU
Depth-Anything	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	51.038 ms	3 - 5 MB	NPU
Depth-Anything	QNN_DLC	float	Qualcomm® SA8775P	56.601 ms	0 - 371 MB	NPU
Depth-Anything	QNN_DLC	float	Qualcomm® SA8650P	56.601 ms	0 - 371 MB	NPU
Depth-Anything	QNN_DLC	float	Qualcomm® SA8255P	56.601 ms	0 - 371 MB	NPU
Depth-Anything	QNN_DLC	float	Qualcomm® QCS8450	92.553 ms	3 - 485 MB	NPU
Depth-Anything	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	56.944 ms	3 - 9 MB	NPU
Depth-Anything	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	51.394 ms	3 - 3 MB	NPU
Depth-Anything	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	24.754 ms	0 - 384 MB	NPU
Depth-Anything	QNN_DLC	float	Qualcomm® SA7255P	142.179 ms	2 - 389 MB	NPU
Depth-Anything	QNN_DLC	float	Qualcomm® SA8295P	82.592 ms	1 - 363 MB	NPU
Depth-Anything	QNN_DLC	float	Snapdragon® 8 Elite Mobile	24.754 ms	0 - 384 MB	NPU
Depth-Anything	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	19.717 ms	3 - 384 MB	NPU
Depth-Anything	QNN_DLC	w8a16	Snapdragon® X2 Elite	71.252 ms	2 - 2 MB	NPU
Depth-Anything	QNN_DLC	w8a16	Snapdragon® X Elite	137.737 ms	2 - 2 MB	NPU
Depth-Anything	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	114.616 ms	0 - 2300 MB	NPU
Depth-Anything	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-8275	136.819 ms	2 - 6 MB	NPU
Depth-Anything	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-8275	259.848 ms	2 - 2002 MB	NPU
Depth-Anything	QNN_DLC	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	169.401 ms	2 - 5 MB	NPU
Depth-Anything	QNN_DLC	w8a16	Qualcomm® SA8775P	141.037 ms	2 - 2000 MB	NPU
Depth-Anything	QNN_DLC	w8a16	Qualcomm® SA8650P	141.037 ms	2 - 2000 MB	NPU
Depth-Anything	QNN_DLC	w8a16	Qualcomm® SA8255P	141.037 ms	2 - 2000 MB	NPU
Depth-Anything	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-9075	154.259 ms	1 - 5 MB	NPU
Depth-Anything	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-X7181	137.737 ms	2 - 2 MB	NPU
Depth-Anything	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-8750	93.709 ms	2 - 2010 MB	NPU
Depth-Anything	QNN_DLC	w8a16	Qualcomm® SA7255P	259.848 ms	2 - 2002 MB	NPU
Depth-Anything	QNN_DLC	w8a16	Snapdragon® 8 Elite Mobile	93.709 ms	2 - 2010 MB	NPU
Depth-Anything	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	81.693 ms	2 - 2013 MB	NPU
Depth-Anything	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	38.789 ms	0 - 518 MB	NPU
Depth-Anything	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	92.25 ms	0 - 487 MB	NPU
Depth-Anything	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	57.55 ms	1 - 58 MB	NPU
Depth-Anything	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	142.42 ms	1 - 396 MB	NPU
Depth-Anything	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	50.601 ms	1 - 11 MB	NPU
Depth-Anything	TFLITE	float	Qualcomm® SA8775P	56.966 ms	1 - 395 MB	NPU
Depth-Anything	TFLITE	float	Qualcomm® SA8650P	56.966 ms	1 - 395 MB	NPU
Depth-Anything	TFLITE	float	Qualcomm® SA8255P	56.966 ms	1 - 395 MB	NPU
Depth-Anything	TFLITE	float	Qualcomm® QCS8450	92.25 ms	0 - 487 MB	NPU
Depth-Anything	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	56.854 ms	1 - 58 MB	NPU
Depth-Anything	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	24.832 ms	1 - 395 MB	NPU
Depth-Anything	TFLITE	float	Qualcomm® SA7255P	142.42 ms	1 - 396 MB	NPU
Depth-Anything	TFLITE	float	Qualcomm® SA8295P	82.515 ms	1 - 370 MB	NPU
Depth-Anything	TFLITE	float	Snapdragon® 8 Elite Mobile	24.832 ms	1 - 395 MB	NPU
Depth-Anything	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	19.797 ms	0 - 392 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.