🧠

Model

Depth Anything V3

Name: Depth Anything V3
Author: qualcomm

by qualcomm hf-model--qualcomm--depth-anything-v3

Nexus Index

38.0 Top 10%

S: Semantic 50

A: Authority 0

P: Popularity 3

R: Recency 99

Q: Quality 50

Tech Context

Vital Performance

33 DL / 30D

0.0%

Source →

Audited 38 FNI Score

Tiny - Params

- Context

33 Downloads

Restricted OTHER License

Model Information Summary
Entity Passport
Registry ID	hf-model--qualcomm--depth-anything-v3
License	Other
Provider	huggingface

📜

Cite this model

Academic & Research Attribution

BibTeX

@misc{hf_model__qualcomm__depth_anything_v3,
  author = {qualcomm},
  title = {Depth Anything V3 Model},
  year = {2026},
  howpublished = {\url{https://huggingface.co/qualcomm/depth-anything-v3}},
  note = {Accessed via Free2AITools Knowledge Fortress}
}

APA Style

qualcomm. (2026). Depth Anything V3 [Model]. Free2AITools. https://huggingface.co/qualcomm/depth-anything-v3

🔬Technical Deep Dive

Full Specifications [+]

Quick Commands

🤗 HF Download

huggingface-cli download qualcomm/depth-anything-v3

⚖️ Nexus Index V2.0

Methodology Index Protocol

38.0

TOP 10% SYSTEM IMPACT

Semantic (S) 50

Authority (A) 0

Popularity (P) 3

Recency (R) 99

Quality (Q) 50

💬 Index Insight

FNI V2.0 for Depth Anything V3: Semantic (S:50), Authority (A:0), Popularity (P:3), Recency (R:99), Quality (Q:50).

Free2AITools Nexus Index

Verification Authority

HuggingFace API GitHub Metadata Arxiv Citation DB System Audit

Unbiased Data Node Refresh: VFS Live

---

🚀 What's Next?

📊

Find Training Datasets

Discover datasets compatible with this model

📈

Compare Benchmarks

See how this model ranks on standard tests

⚡

Technical Deep Dive

Depth-Anything-V3: Optimized for Qualcomm Devices

Depth Anything 3 (DA3), a model that predicts spatially consistent geometry from arbitrary visual inputs, with or without known camera poses.

This is based on the implementation of Depth-Anything-V3 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
QNN_DLC	float	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-V3 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-V3 on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.depth_estimation

Model Stats:

Model checkpoint: da3-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-V3	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	34.313 ms	5 - 601 MB	NPU
Depth-Anything-V3	ONNX	float	Snapdragon® X2 Elite	35.56 ms	71 - 71 MB	NPU
Depth-Anything-V3	ONNX	float	Snapdragon® X Elite	75.07 ms	70 - 70 MB	NPU
Depth-Anything-V3	ONNX	float	Snapdragon® 8 Gen 3 Mobile	59.025 ms	1 - 755 MB	NPU
Depth-Anything-V3	ONNX	float	Qualcomm® QCS8550 (Proxy)	74.002 ms	0 - 80 MB	NPU
Depth-Anything-V3	ONNX	float	Qualcomm® QCS9075	104.563 ms	3 - 9 MB	NPU
Depth-Anything-V3	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	39.529 ms	2 - 562 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	34.249 ms	3 - 596 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Snapdragon® X2 Elite	35.621 ms	3 - 3 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Snapdragon® X Elite	78.247 ms	3 - 3 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	54.645 ms	2 - 743 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	177.731 ms	0 - 561 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	76.66 ms	3 - 6 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Qualcomm® SA8775P	82.39 ms	1 - 564 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Qualcomm® QCS9075	107.182 ms	3 - 9 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	134.58 ms	3 - 772 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Qualcomm® SA7255P	177.731 ms	0 - 561 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Qualcomm® SA8295P	121.077 ms	3 - 571 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	40.642 ms	3 - 584 MB	NPU
Depth-Anything-V3	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	30.766 ms	1 - 549 MB	NPU
Depth-Anything-V3	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	48.423 ms	1 - 691 MB	NPU
Depth-Anything-V3	TFLITE	float	Qualcomm® QCS8275 (Proxy)	164.442 ms	0 - 529 MB	NPU
Depth-Anything-V3	TFLITE	float	Qualcomm® QCS8550 (Proxy)	67.175 ms	1 - 5 MB	NPU
Depth-Anything-V3	TFLITE	float	Qualcomm® SA8775P	73.663 ms	1 - 531 MB	NPU
Depth-Anything-V3	TFLITE	float	Qualcomm® QCS9075	86.491 ms	1 - 82 MB	NPU
Depth-Anything-V3	TFLITE	float	Qualcomm® QCS8450 (Proxy)	103.313 ms	0 - 691 MB	NPU
Depth-Anything-V3	TFLITE	float	Qualcomm® SA7255P	164.442 ms	0 - 529 MB	NPU
Depth-Anything-V3	TFLITE	float	Qualcomm® SA8295P	97.772 ms	1 - 521 MB	NPU
Depth-Anything-V3	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	34.571 ms	0 - 535 MB	NPU

License

The license for the original implementation of Depth-Anything-V3 can be found here.

References

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.

⚠️ Incomplete Data

Some information about this model is not available. Use with Caution - Verify details from the original source before relying on this data.

View Original Source →

📝 Limitations & Considerations

• Benchmark scores may vary based on evaluation methodology and hardware configuration.
• VRAM requirements are estimates; actual usage depends on quantization and batch size.
• FNI scores are relative rankings and may change as new models are added.
⚠ License Unknown: Verify licensing terms before commercial use.

Top Tier

Social Proof

HuggingFace Hub

33Downloads

Hub Discussions

🤗 Data Source: Hugging Face ↗

🔄 Daily sync (03:00 UTC)

AI Summary: Based on Hugging Face metadata. Not a recommendation.

📊 FNI Methodology 📚 Knowledge Baseℹ️ Verify with original source

🛡️ Model Transparency Report

Technical metadata sourced from upstream repositories.

Open Metadata

🆔 Identity & Source

id: hf-model--qualcomm--depth-anything-v3
slug: qualcomm--depth-anything-v3
source: huggingface
author: qualcomm
license: Other
tags: pytorch, android, depth-estimation, arxiv:2511.10647, license:other, region:us

⚙️ Technical Specs

architecture: null
params billions: null
context length: null
pipeline tag: depth-estimation

📊 Engagement & Metrics

downloads: 33
stars: 0
forks: 0

Data indexed from public sources. Updated daily.

Welcome to Free2AI Tools!

Smart Search

FNI Score

You're All Set!