---
license: apache-2.0
base_model: lightonai/LightOnOCR-3-4B
base_model_relation: quantized
pipeline_tag: image-text-to-text
tags:
  - gguf
  - llama.cpp
  - ocr
  - document-understanding
  - vision-language
---

# LightOnOCR-3-4B GGUF (Q8_0)

GGUF conversion of [LightOnOCR-3-4B](https://huggingface.co/lightonai/LightOnOCR-3-4B) for [llama.cpp](https://github.com/ggml-org/llama.cpp). LightOnOCR-3-4B is an end-to-end OCR vision-language model that turns a document page image into Markdown, with tables as HTML.

## Files

| File | Contents | Precision | Size | SHA256 |
|---|---|---|---|---|
| `model.gguf` | Language model | Q8_0 | 4.48 GB | `39af92d0e22c262fdd1e611b0062c33961ad69c5166562172097c17cfdd4cfec` |
| `mmproj.gguf` | Vision encoder and projector | F16 | 0.67 GB | `486a4675f31a9b6d741c95e4605632c95d9b151c25eca22bcf1eddfee6cf901f` |

## Original model

- **Model:** [lightonai/LightOnOCR-3-4B](https://huggingface.co/lightonai/LightOnOCR-3-4B)
- **Author:** [LightOn](https://lighton.ai)
- **Architecture:** Qwen3.5 vision-language (4B)
- **Paper:** [LightOnOCR: A 1B End-to-End Multilingual Vision-Language Model for State-of-the-Art OCR](https://arxiv.org/abs/2601.14251)
- **Code:** [github.com/lightonai/LightOnOCR](https://github.com/lightonai/LightOnOCR)

## Conversion

Converted from the official `model.safetensors` with llama.cpp's `convert_hf_to_gguf.py`:

- language model exported directly as Q8_0;
- vision encoder and projector exported as F16 (`--mmproj`);
- `--no-mtp`, because the upstream checkpoint ships without the multi-token-prediction head (`mtp_num_hidden_layers: 0`).

No other changes were made to the weights. The upstream chat template is embedded in `model.gguf`.

## Usage with llama.cpp

```bash
llama-server -m model.gguf --mmproj mmproj.gguf --reasoning off
```

- **`--reasoning off` is required.** Without it llama-server enables the Qwen3.5 thinking mode, and the transcription ends up in `reasoning_content` while `content` is empty.
- **Send the image only.** As described in the [upstream model card](https://huggingface.co/lightonai/LightOnOCR-3-4B), transcription mode takes the page image with an empty prompt. Other instructions are out of distribution for the model.
- **Image size:** the upstream card recommends rendering PDF pages at 400 DPI and resizing so the longest side is 2048 px.

Example request body for `/v1/chat/completions`:

```json
{
  "messages": [
    {
      "role": "user",
      "content": [
        { "type": "image_url", "image_url": { "url": "data:image/png;base64,..." } }
      ]
    }
  ],
  "temperature": 0
}
```

## License

LightOnOCR-3-4B is released by LightOn under the [Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0), for research and commercial use. Its base architecture, Qwen3.5, is also released under the Apache License 2.0.

This repository redistributes the model under the same license. The files are a modified form of the original weights: they were converted to the GGUF format and the language model was quantized to Q8_0.

## Citation

```bibtex
@misc{lightonocr2_2026,
  title        = {LightOnOCR: A 1B End-to-End Multilingual Vision-Language Model for State-of-the-Art OCR},
  author       = {Said Taghadouini and Adrien Cavaill\`{e}s and Baptiste Aubertin},
  year         = {2026},
  howpublished = {\url{https://arxiv.org/abs/2601.14251}}
}
```

---
*Hosted by [deAPI-ai](https://huggingface.co/deAPI-ai) for use with [GamerHash AI](https://gamerhash.com)*