<!-- # hard line break macro for HTML -->

<a id="model-zoo-dinov3-vitb16-torch"></a>

# dinov3-vitb16-torch

DINOv3 ViT-B/16 self-supervised image embeddings pretrained on LVD-1689M (1.7B images). Requires accepting the DINOv3 license on Hugging Face.

**Details**

- Model name: `dinov3-vitb16-torch`
- Model source: [https://huggingface.co/facebook/dinov3-vitb16-pretrain-lvd1689m](https://huggingface.co/facebook/dinov3-vitb16-pretrain-lvd1689m)
- Model author: Oriane Simeoni, et al.
- Model license: DINOv3 License
- Model size: 326.79 MB
- Exposes embeddings? yes
- Tags: `embeddings, torch, dinov3, transformer, official`

**Requirements**

- Packages: `torch, torchvision, transformers>=4.56`
- CPU support
  - yes
- GPU support
  - yes

**Example usage**

```python
import fiftyone as fo
import fiftyone.zoo as foz

dataset = foz.load_zoo_dataset(
    "coco-2017",
    split="validation",
    dataset_name=fo.get_default_dataset_name(),
    max_samples=50,
    shuffle=True,
)

model = foz.load_zoo_model("dinov3-vitb16-torch")

dataset.apply_model(model, label_field="predictions")

session = fo.launch_app(dataset)
```