---
title: DeepSeek-OCR-2-5bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/DeepSeek-OCR-2-5bit"
md_url: "https://www.modelscope.cn/models/mlx-community/DeepSeek-OCR-2-5bit.md"
repository: mlx-community/DeepSeek-OCR-2-5bit
last_updated: 2026-01-28
license: apache-2.0
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
model_type:
  - deepseekocr_2
architectures:
  - DeepseekOCR2ForCausalLM
parameters: 1.0B
tensor_type:
  - BF16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - multilingual
downloads: 76
stars: 0
tags:
  - deepseek
  - vision-language
  - ocr
  - custom_code
  - mlx
---

# DeepSeek-OCR-2-5bit

> DeepSeek-OCR-2-5bit - mlx-community 在 ModelScope 开源的模型。mlx-community/DeepSeek-OCR-2-5bit This model was converted to MLX format from prince-canuma/DeepSeek-OCR-2 using mlx-vlm version 0.3.10. Refer to the original model card for more details on the model.…

mlx-community/DeepSeek-OCR-2-5bit 是 ModelScope 魔搭社区上的 1.0B 参数image-text-to-text模型，采用 apache-2.0 许可。

- **Repository**: mlx-community/DeepSeek-OCR-2-5bit
- **License**: apache-2.0
- **Tasks**: image-text-to-text
- **Parameters**: 1.0B
- **Tags**: deepseek, vision-language, ocr, custom_code, mlx
- **Downloads**: 76
- **Stars**: 0
- **Last updated**: 2026-01-28

Source: https://www.modelscope.cn/models/mlx-community/DeepSeek-OCR-2-5bit

---

# mlx-community/DeepSeek-OCR-2-5bit
This model was converted to MLX format from [`prince-canuma/DeepSeek-OCR-2`]() using mlx-vlm version **0.3.10**.
Refer to the [original model card](https://huggingface.co/prince-canuma/DeepSeek-OCR-2) for more details on the model.
## Use with mlx

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

```bash
python -m mlx_vlm.generate --model mlx-community/DeepSeek-OCR-2-5bit --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
```