---
license: apache-2.0
language:
- en
pipeline_tag: image-text-to-text
tags:
- multimodal
base_model:
- Qwen/Qwen2-VL-2B-Instruct
---

# Inference:
```bash
./llama-qwen2vl-cli -m Q8_0.gguf --mmproj qwen2vl-vision.gguf -p "Describe this image." --image "demo.jpg"
```

## Converted using this Colab Notebook:
**[Colab Notebook](https://colab.research.google.com/drive/1RBb8Iw3GNWx2jhb3n7hKyHJHfHVICivz?usp=sharing)**

## Special Thanks to:
**HimariO** for the excellent work on enabling quantization for Qwen2-VL! [PR on GitHub](https://github.com/ggerganov/llama.cpp/pull/10361)