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:
CPU friendly: Even on CPUs, Namo R1 can runs very fast;
Omni-modal Scalability: Native support for future expansion into audio (ASR/TTS) and cross-modal fusion;
Training Transparency: Full disclosure of data curation processes and dynamic curriculum scheduling techniques.
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
Namo-700M
training
training
700M
Namo-500M-R1
training
training
500M
Namo-700M-R1
training
training
700M
SmolVLM-500M
53.8
35.4
500M
SmolVLM-Instruct-DPO
67.5
49.8
2.3B
Moondream1
62.3
19.8
1.9B
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:
pip install -U namo
A simple demo would be:
python
1from namo.api.vl import VLInfer
23# model will download automatically4model = VLInfer(model_type='namo')56# default will have streaming7model.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
namo server --model checkpoints/Namo-500M-V1
then, you will have OpenAI like serving in local.
Features of Namo R1
In contrast to open-source VLMs like Qwen2.5-3B and MiniCPM, the Namo series offers the following features that enable anyone to train their own VLMs from scratch:
Extremely Small: Our first series has only 500 million parameters yet powerful on various tasks.
OCR Capability: With just a 500M model, you can perform multilingual OCR, covering not only Chinese and English but also Japanese and other languages.
Dynamic Resolution: We support native dynamic resolution as input, making it robust for images of any ratio.
Fully Open Source: We opensource all model codes including training steps and scripts!
R1 Support: Yes, we now support R1 for post-training.
Above all, we are also ready to help when u want train your MLLM from scratch at any tasks!
Roadmap
We are still actively training on new models, here are few things we will arrive:
Speech model;
Vision model with more decent vision encoders, such as SigLip2;
TTS ability;
Slightly larger models, up to 7B;
Trouble Shooting
Got error when using deepspeed: AssertionError: no_sync context manager is incompatible with gradient partitioning logic of ZeRO stage 2 ?
Please upgrade transformers to 4.48+ and use latest deepspeed.
Copyright
All right reserved by Namo authors, code released under MIT License.
