---
title: chandra-8bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/chandra-8bit"
md_url: "https://www.modelscope.cn/models/mlx-community/chandra-8bit.md"
repository: mlx-community/chandra-8bit
last_updated: 2025-10-22
license: openrail
model_type:
  - qwen3_vl
architectures:
  - Qwen3VLForConditionalGeneration
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 111
stars: 0
tags:
  - ocr
  - vlm
  - mlx
---

# chandra-8bit

> chandra-8bit - mlx-community 在 ModelScope 开源的模型。mlx-community/chandra-8bit This model was converted to MLX format from datalab-to/chandra using mlx-vlm version 0.3.4. Refer to the original model card for more details on the model. Use with mlx

mlx-community/chandra-8bit 是 ModelScope 魔搭社区上的机器学习模型，采用 openrail 许可。

- **Repository**: mlx-community/chandra-8bit
- **License**: openrail
- **Tags**: ocr, vlm, mlx
- **Downloads**: 111
- **Stars**: 0
- **Last updated**: 2025-10-22

Source: https://www.modelscope.cn/models/mlx-community/chandra-8bit

---

# mlx-community/chandra-8bit
This model was converted to MLX format from [`datalab-to/chandra`]() using mlx-vlm version **0.3.4**.
Refer to the [original model card](https://huggingface.co/datalab-to/chandra) for more details on the model.
## Use with mlx

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

```bash
python -m mlx_vlm.generate --model mlx-community/chandra-8bit --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
```