🤗 Namo-500M-V1 | 🐝 Community
**You**: *I don't have GPUs to run VLMs.* **Namo R1:** Hold my beer.... let's do this on CPU. **Namo R1** 🔥🔥 surpassed SmolVLM and Moondream2 in terms of same size! And we are keep evolving, more advanced models are under training! ## Introduction We are excited to open-source **Namo**, an extremly small yet mighty MLLM. While numerous MLLMs exist, few offer true extensibility or fully open-source their training data, model architectures, and training schedulers - critical components for reproducible AI research. The AI community has largely overlooked the potential of compact MLLMs, despite their demonstrated efficiency advantages. Our analysis reveals significant untapped potential in sub-billion parameter models, particularly for edge deployment and specialized applications. To address this gap, we're releasing Namo R1, a foundational 500M parameter model trained from scratch using innovative architectural choices. Key innovations include: 1. **CPU friendly:** Even on CPUs, Namo R1 can runs very fast; 2. **Omni-modal Scalability:** Native support for future expansion into audio (ASR/TTS) and cross-modal fusion; 3. **Training Transparency:** Full disclosure of data curation processes and dynamic curriculum scheduling techniques. 👇 Video Demo Runs on **CPU**: ## Updates - **`2025.02.21`**: more to come...! - **`2025.02.21`**: 🔥🔥 The first version is ready to open, fire the MLLM power able to runs on CPU! - **`2025.02.17`**: Namo R1 start training. ## Results the result might keep updating as new models trained. | Model | MMB-EN-T | MMB-CN-T | Size | | -------------------- | -------- | -------- | ---- | | Namo-500M | 68.8 | 48.7 | 500M | | SmolVLM-500M | 53.8 | 35.4 | 500M | | SmolVLM-Instruct-DPO | 67.5 | 49.8 | 2.3B | | Moondream2 | 70 | 28.7 | 1.9B | ⚠️ Currently, the testing has only been conducted on a limited number of benchmarks. In the near future, more metrics will be reported. Even so, we've observed significant improvements compared to other small models. ## Get Started #### Install & Run in Cli All you need to do is: ```shell pip install -U namo ``` A simple demo would be: ```python from namo.api.vl import VLInfer # model will download automatically model = VLInfer(model_type='namo') # default will have streaming model.generate('what is this?', 'images/cats.jpg', stream=True) ``` That's all! For cli multi-turn chat in terminal you can run `python demo.py`. (Namo cli directly in your terminal would be avaiable later.) #### OpenAI server & Run in OpenWebUI ```shell namo server --model checkpoints/Namo-500M-V1 ``` then, you will have OpenAI like serving in local. ## Showcases **Namo-500M**, our first small series of models, is capable of performing remarkable tasks such as multilingual OCR, general concept understanding, image captioning, and more. And it has only 500 million parameters! You can run it directly on a CPU!