---
title: EdgeTAM
canonical_url: "https://www.modelscope.cn/models/facebook/EdgeTAM"
md_url: "https://www.modelscope.cn/models/facebook/EdgeTAM.md"
repository: facebook/EdgeTAM
last_updated: 2025-05-20
license: apache-2.0
library_name:
  - pytorch
frameworks:
  - pytorch
downloads: 334
stars: 0
---

# EdgeTAM

> EdgeTAM - facebook 在 ModelScope 开源的模型。[\[📃 Tech Report\]](https://arxiv.org/abs/2501.07256) [\[📂 Github\]](https://github.com/facebookresearch/EdgeTAM) [\[🤗 Demo\]](https://huggingface.co/spaces/facebook/EdgeTAM)

facebook/EdgeTAM 是 ModelScope 魔搭社区上的机器学习模型，采用 apache-2.0 许可。

- **Repository**: facebook/EdgeTAM
- **License**: apache-2.0
- **Downloads**: 334
- **Stars**: 0
- **Last updated**: 2025-05-20

Source: https://www.modelscope.cn/models/facebook/EdgeTAM

---

# Model Details

[\[📃 Tech Report\]](https://arxiv.org/abs/2501.07256)
[\[📂 Github\]](https://github.com/facebookresearch/EdgeTAM)
[\[🤗 Demo\]](https://huggingface.co/spaces/facebook/EdgeTAM)

EdgeTAM is an on-device executable variant of the SAM 2 for promptable segmentation and tracking in videos. It runs 22× faster than SAM 2 and achieves 16 FPS on iPhone 15 Pro Max without quantization.

# How to use

We provide the inference code with local deployment instructions in https://github.com/facebookresearch/EdgeTAM.
You can find more details in the GitHub repo.

# Citation
If you find our code useful for your research, please consider citing:
    
```
@article{zhou2025edgetam,
  title={EdgeTAM: On-Device Track Anything Model},
  author={Zhou, Chong and Zhu, Chenchen and Xiong, Yunyang and Suri, Saksham and Xiao, Fanyi and Wu, Lemeng and Krishnamoorthi, Raghuraman and Dai, Bo and Loy, Chen Change and Chandra, Vikas and Soran, Bilge},
  journal={arXiv preprint arXiv:2501.07256},
  year={2025}
}
```