These files are compatible with llama.cpp, Ollama, and other GGUF-based tools, supporting inference on CPU, NVIDIA GPU (CUDA), Apple Silicon (Metal), Intel GPUs (SYCL), and more. You can mix precision levels for the language and vision components based on your hardware and performance needs, and even perform custom quantization starting from the FP16 weights.

Enjoy running this multimodal model on your personal device! 🚀

How to Use

To use these models with llama.cpp, please ensure you are using the latest version—either by building from source or downloading the most recent release according to the devices.

You can run inference via the command line or through a web-based chat interface.

CLI Inference (`llama-mtmd-cli`)

For example, to run ZwZ-2B with an Q8_0 vision encoder and Q8_0 quantized LLM:

bash

llama-mtmd-cli \
  -m path/to/ZwZ-2B-Q8_0.gguf \
  --mmproj mmproj-ZwZ-2B-Q8_0.gguf\
  --image test.jpeg \
  -p "What is the publisher name of the newspaper?" \
  --temp 1.0 --top-k 20 --top-p 0.95 -n 1024

Web Chat (using `llama-server`)

To serve ZwZ-2B via an OpenAI-compatible API with a web UI:

bash

llama-server \
  -m path/to/ZwZ-2B-Q8_0.gguf  \
  --mmproj mmproj-ZwZ-2B-Q8_0.gguf

Citation

bibtex

@article{wei2026zooming,
  title={Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perception},
  author={Wei, Lai and He, Liangbo and Lan, Jun and Dong, Lingzhong and Cai, Yutong and Li, Siyuan and Zhu, Huijia and Wang, Weiqiang and Kong, Linghe and Wang, Yue and Zhang, Zhuosheng and Huang, Weiran},
  journal={arXiv preprint arXiv:2602.11858},
  year={2026}
}

License

This model follows the license of Apache 2.0 License.

inclusionAI/ZwZ-2B-GGUF

How to Use

CLI Inference (llama-mtmd-cli)

Web Chat (using llama-server)

Citation

License

inclusionAI/
ZwZ-2B-GGUF

CLI Inference (`llama-mtmd-cli`)

Web Chat (using `llama-server`)