---
title: LightOnOCR-3-1B-mlx-8bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/LightOnOCR-3-1B-mlx-8bit"
md_url: "https://www.modelscope.cn/models/mlx-community/LightOnOCR-3-1B-mlx-8bit.md"
repository: mlx-community/LightOnOCR-3-1B-mlx-8bit
last_updated: 2026-10-17
license: apache-2.0
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
model_type:
  - mistral3
architectures:
  - LightOnOCRForConditionalGeneration
base_model:
  - lightonai/LightOnOCR-3-1B
base_model_relation: quantized
parameters: 577.3M
tensor_type:
  - U32
  - BF16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 37
stars: 0
tags:
  - ocr
  - document-understanding
  - visual-grounding
  - vision-language
  - tables
  - forms
  - mlx
---

# LightOnOCR-3-1B-mlx-8bit

> LightOnOCR-3-1B-mlx-8bit - mlx-community 在 ModelScope 开源的模型。mlx-community/LightOnOCR-3-1B-mlx-8bit

mlx-community/LightOnOCR-3-1B-mlx-8bit 是 ModelScope 魔搭社区上的 577.3M 参数image-text-to-text模型，采用 apache-2.0 许可，基于 lightonai/LightOnOCR-3-1B 构建。

- **Repository**: mlx-community/LightOnOCR-3-1B-mlx-8bit
- **License**: apache-2.0
- **Tasks**: image-text-to-text
- **Parameters**: 577.3M
- **Base model**: lightonai/LightOnOCR-3-1B
- **Tags**: ocr, document-understanding, visual-grounding, vision-language, tables, forms, mlx
- **Downloads**: 37
- **Stars**: 0
- **Last updated**: 2026-10-17

Source: https://www.modelscope.cn/models/mlx-community/LightOnOCR-3-1B-mlx-8bit

---

# mlx-community/LightOnOCR-3-1B-mlx-8bit

This model was converted to MLX format from [`lightonai/LightOnOCR-3-1B`](https://huggingface.co/lightonai/LightOnOCR-3-1B)
using mlx-vlm version **0.6.8**.
Refer to the [original model card](https://huggingface.co/lightonai/LightOnOCR-3-1B) for more details on the model.

## Use with mlx

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

```bash
python -m mlx_vlm.generate --model mlx-community/LightOnOCR-3-1B-mlx-8bit --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
```