Instructions to use deAPI-ai/lightonocr-3-4b-q8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use deAPI-ai/lightonocr-3-4b-q8 with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf deAPI-ai/lightonocr-3-4b-q8
# Run inference directly in the terminal:
llama cli -hf deAPI-ai/lightonocr-3-4b-q8

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf deAPI-ai/lightonocr-3-4b-q8
# Run inference directly in the terminal:
llama cli -hf deAPI-ai/lightonocr-3-4b-q8

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf deAPI-ai/lightonocr-3-4b-q8
# Run inference directly in the terminal:
./build/bin/llama cli -hf deAPI-ai/lightonocr-3-4b-q8

Use Docker

docker model run hf.co/deAPI-ai/lightonocr-3-4b-q8

Llama new
LM Studio
Jan

vLLM

How to use deAPI-ai/lightonocr-3-4b-q8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deAPI-ai/lightonocr-3-4b-q8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deAPI-ai/lightonocr-3-4b-q8",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/deAPI-ai/lightonocr-3-4b-q8

Ollama
How to use deAPI-ai/lightonocr-3-4b-q8 with Ollama:
```
ollama run hf.co/deAPI-ai/lightonocr-3-4b-q8
```
Unsloth Desktop

How to use deAPI-ai/lightonocr-3-4b-q8 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf deAPI-ai/lightonocr-3-4b-q8

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "deAPI-ai/lightonocr-3-4b-q8"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use deAPI-ai/lightonocr-3-4b-q8 with Docker Model Runner:
```
docker model run hf.co/deAPI-ai/lightonocr-3-4b-q8
```

Lemonade

How to use deAPI-ai/lightonocr-3-4b-q8 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull deAPI-ai/lightonocr-3-4b-q8

Run and chat with the model

lemonade run user.lightonocr-3-4b-q8-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use deAPI-ai/lightonocr-3-4b-q8 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf deAPI-ai/lightonocr-3-4b-q8

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default deAPI-ai/lightonocr-3-4b-q8

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use deAPI-ai/lightonocr-3-4b-q8 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf deAPI-ai/lightonocr-3-4b-q8

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "deAPI-ai/lightonocr-3-4b-q8" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

lightonocr-3-4b-q8 / README.md

dawidope

Upload LightOnOCR-3-4B GGUF (v1)

87571a3 verified 1 day ago

preview code

Raw History Blame Contribute Delete

3.5 kB

---
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)*

	---
	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)