---
library_name: transformers
license: apache-2.0
datasets:
- HuggingFaceM4/the_cauldron
- HuggingFaceM4/Docmatix
- lmms-lab/LLaVA-OneVision-Data
- lmms-lab/M4-Instruct-Data
- HuggingFaceFV/finevideo
- MAmmoTH-VL/MAmmoTH-VL-Instruct-12M
- lmms-lab/LLaVA-Video-178K
- orrzohar/Video-STaR
- Mutonix/Vript
- TIGER-Lab/VISTA-400K
- Enxin/MovieChat-1K_train
- ShareGPT4Video/ShareGPT4Video
pipeline_tag: video-text-to-text
language:
- en
base_model:
- HuggingFaceTB/SmolVLM-Instruct
tags:
- mlx
---

# smdesai/SmolVLM2-2.2B-Instruct-4bit
This model was converted to MLX format from [`HuggingFaceTB/SmolVLM2-2.2B-Instruct`]() using mlx-vlm version **0.1.14**.
Refer to the [original model card](https://huggingface.co/HuggingFaceTB/SmolVLM2-2.2B-Instruct) for more details on the model.
## Use with mlx

```bash
pip install -U mlx-vlm
```

```bash
python -m mlx_vlm.generate --model smdesai/SmolVLM2-2.2B-Instruct-4bit --max-tokens 100 --temp 0.0 --prompt "Describe this image." --image <path_to_image>
```