---
license: cc-by-nc-4.0
---

# Mobile-VideoGPT-0.5B

---
## 📝 Description
Mobile-VideoGPT is an efficient multimodal framework designed to operate with fewer than a billion parameters. Unlike traditional video large multimodal models, Mobile-VideoGPT consists of lightweight dual visual encoders, efficient projectors, and a small language model (SLM) with real-time throughput. We evaluate our model across well-established six video understanding benchmarks (e.g., MVBench, EgoSchema, NextQA, and PerceptionTest), and our results show that Mobile-VideoGPT-0.5B can generate up to 46 tokens per second while outperforming existing state-of-the-art 0.5B-parameter competitors.

**This model contains Mobile-VideoGPT checkpoints with Qwen-2.5-0.5B LLM**

## 💻 Download
To get started, follow these steps:
   ```
   git lfs install
   git clone https://huggingface.co/Amshaker/Mobile-VideoGPT-0.5B
   ```

## 📚 Additional Resources
- **Paper:** [ArXiv]().
- **GitHub Repository:** For training and evaluation: [GitHub - Mobile-VideoGPT](https://github.com/Amshaker/Mobile-VideoGPT).

## 📜 Citations:

```bibtex
    @article{Shaker2025MobileVideoGPT,
        title={Mobile-VideoGPT: Fast and Accurate Video Understanding Language Model},
        author={Shaker, Abdelrahman and Maaz, Muhammad and Rezatofighi, Hamid and Khan, Salman and Khan, Fahad Shahbaz},
        journal={arxiv},
        year={2025},
        url={https://arxiv.org/abs/2503.21782}
    }