---
title: DeepSeek-OCR-GGUF
canonical_url: "https://www.modelscope.cn/models/NexaAIDev/DeepSeek-OCR-GGUF"
md_url: "https://www.modelscope.cn/models/NexaAIDev/DeepSeek-OCR-GGUF.md"
repository: NexaAIDev/DeepSeek-OCR-GGUF
last_updated: 2025-11-15
base_model:
  - deepseek-ai/DeepSeek-OCR
base_model_relation: quantized
library_name:
  - gguf
  - pytorch
frameworks:
  - pytorch
language:
  - multilingual
downloads: 1856
stars: 2
tags:
  - deepseek
  - vision-language
  - ocr
  - document-parse
  - gguf
---

# DeepSeek-OCR-GGUF

> DeepSeek-OCR-GGUF - NexaAIDev 在 ModelScope 开源的模型。[!NOTE] Note currently only NexaSDK supports this model's GGUF.

NexaAIDev/DeepSeek-OCR-GGUF 是 ModelScope 魔搭社区上的机器学习模型，基于 deepseek-ai/DeepSeek-OCR 构建。

- **Repository**: NexaAIDev/DeepSeek-OCR-GGUF
- **Base model**: deepseek-ai/DeepSeek-OCR
- **Tags**: deepseek, vision-language, ocr, document-parse, gguf
- **Downloads**: 1856
- **Stars**: 2
- **Last updated**: 2025-11-15

Source: https://www.modelscope.cn/models/NexaAIDev/DeepSeek-OCR-GGUF

---

# DeepSeek OCR

> [!NOTE]  
> Note currently only [NexaSDK](https://github.com/NexaAI/nexa-sdk) supports this model's GGUF.

## Quickstart

1. **Install [NexaSDK](https://github.com/NexaAI/nexa-sdk)**
2. Run the model locally with one line of code:

   ```bash
   nexa infer NexaAI/DeepSeek-OCR-GGUF
   ```
3. Then drag your image to terminal or type into the image path


case 1 : extract text
```bash
<your-image-path> Free OCR.
```


case 2 : extract bounding box
```bash
<your-image-path> <|grounding|>Convert the document to markdown. 
```
> Note: If the model fails to run, install the latest [Vulkan driver for Windows](https://www.amd.com/en/support/download/drivers.html)

## Model Description
**DeepSeek OCR** is a high-accuracy optical character recognition model built for extracting text from complex visual inputs such as documents, screenshots, receipts, and natural scenes.  
It combines vision-language modeling with efficient visual encoders to achieve superior recognition of multi-language and multi-layout text while remaining lightweight enough for edge or on-device deployment.

## Features
- **Multilingual OCR** — recognizes printed and handwritten text across major global languages.  
- **Document Layout Understanding** — preserves structure such as tables, paragraphs, and titles.  
- **Scene Text Recognition** — robust against lighting, distortion, and low-quality captures.  
- **Lightweight & Fast** — optimized for CPU and GPU acceleration.  
- **End-to-End Pipeline** — supports image-to-text and structured JSON output.  

## Use Cases
- Digitizing scanned documents or PDFs  
- Extracting text from mobile camera inputs or screenshots  
- Invoice and receipt parsing  
- OCR-based search and indexing systems  
- Visual question answering or document agents  

## Inputs and Outputs
**Input:**  
- Image file (JPEG, PNG, or tensor array)  
- Optional parameters for language hints or layout detection  

**Output:**  
- Extracted text (plain text or structured format with bounding boxes)  
- Confidence scores per word or region  

## Integration
DeepSeek OCR can be integrated through:  
- Python API (`pip install deepseek-ocr`)  
- REST or gRPC endpoints for server deployment  

## License
This model is released under the **Apache 2.0 License**, allowing commercial use, modification, and redistribution with attribution.