Instructions to use Abiray/OvisOCR2-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Abiray/OvisOCR2-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Abiray/OvisOCR2-GGUF",
	filename="OvisOCR2-BF16.gguf",
)

llm.create_chat_completion(
	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"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Abiray/OvisOCR2-GGUF 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 Abiray/OvisOCR2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Abiray/OvisOCR2-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Abiray/OvisOCR2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Abiray/OvisOCR2-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Abiray/OvisOCR2-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Abiray/OvisOCR2-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Abiray/OvisOCR2-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Abiray/OvisOCR2-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Abiray/OvisOCR2-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use Abiray/OvisOCR2-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Abiray/OvisOCR2-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Abiray/OvisOCR2-GGUF",
		"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/Abiray/OvisOCR2-GGUF:Q4_K_M

Ollama
How to use Abiray/OvisOCR2-GGUF with Ollama:
```
ollama run hf.co/Abiray/OvisOCR2-GGUF:Q4_K_M
```

Unsloth Studio

How to use Abiray/OvisOCR2-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Abiray/OvisOCR2-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Abiray/OvisOCR2-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Abiray/OvisOCR2-GGUF to start chatting

How to use Abiray/OvisOCR2-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Abiray/OvisOCR2-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Abiray/OvisOCR2-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Abiray/OvisOCR2-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Abiray/OvisOCR2-GGUF:Q4_K_M

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 Abiray/OvisOCR2-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use Abiray/OvisOCR2-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Abiray/OvisOCR2-GGUF:Q4_K_M

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 "Abiray/OvisOCR2-GGUF:Q4_K_M" \
  --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"

Docker Model Runner
How to use Abiray/OvisOCR2-GGUF with Docker Model Runner:
```
docker model run hf.co/Abiray/OvisOCR2-GGUF:Q4_K_M
```

Lemonade

How to use Abiray/OvisOCR2-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Abiray/OvisOCR2-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.OvisOCR2-GGUF-Q4_K_M

List all available models

lemonade list

OvisOCR2 - GGUF Quantizations

Ovis

This repository contains GGUF format quantizations of OvisOCR2, a compact 0.8B end-to-end model for page-level document parsing. The original model was developed by ATH-MaaS by post-training Qwen3.5-0.8B to parse full document pages directly into clean Markdown (including LaTeX formulas, HTML tables, and layout components).

OvisOCR2 establishes a new state-of-the-art for compact document understanding, scoring 96.58 on OmniDocBench v1.6 and outperforming traditional, multi-stage layout analysis pipelines.

Available Files

Main Text Models

File Name	Precision / Quantization	File Size	Description
`OvisOCR2-F16.gguf`	16-bit Float	1.52 GB	Baseline unquantized model
`OvisOCR2-BF16.gguf`	16-bit Brain Float	1.52 GB	Native weight precision
`OvisOCR2-Q8_0.gguf`	8-bit	812 MB	Near-identical precision to F16
`OvisOCR2-Q6_K.gguf`	6-bit	630 MB	Excellent balance of size and accuracy
`OvisOCR2-Q5_K_M.gguf`	5-bit (Medium)	578 MB	Recommended for low-resource deployment
`OvisOCR2-Q5_K_S.gguf`	5-bit (Small)	564 MB	Highly optimized 5-bit layout
`OvisOCR2-Q4_K_M.gguf`	4-bit (Medium)	529 MB	Standard 4-bit quantization
`OvisOCR2-Q4_K_S.gguf`	4-bit (Small)	505 MB	Lightweight 4-bit footprint
`OvisOCR2-Q3_K_M.gguf`	3-bit (Medium)	466 MB	Maximum compression ratio

Multimodal Projectors (`mmproj`)

Note: Because OvisOCR2 is a vision-language model, you must download one of these image processing units alongside your choice of the text models listed above.

mmproj-F32.gguf (402 MB) - Unquantized full precision projector.
mmproj-F16.gguf (205 MB) - Recommended standard performance/size option.
mmproj-BF16.gguf (207 MB) - Target alternative precision layout.

Inference Guide (`llama.cpp`)

To run multimodal OCR tasks using these GGUF files, you need to use the llama-minicpmv-cli or llama-llava-cli tool (depending on your build version of llama.cpp) to handle simultaneous image and text tokens.

Basic Command Line Example

# Run parsing via llama.cpp cli tools
./llama-minicpmv-cli \
  -m OvisOCR2-Q5_K_M.gguf \
  --mmproj mmproj-F16.gguf \
  --image /path/to/your/document_page.jpg \
  -p "<|im_start|>user\nExtract all readable content from the image in natural human reading order and output the result as a single Markdown document. Format formulas as LaTeX. Format tables as HTML: <table>...</table>. Preserve the original text without translation.<|im_end|>\n<|im_start|>assistant\n" \
  -n 4096 \
  --temp 0.0

Downloads last month: 395

GGUF

Model size

0.8B params

Architecture

qwen35

Hardware compatibility

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for Abiray/OvisOCR2-GGUF

Base model

Qwen/Qwen3.5-0.8B-Base

Finetuned

Qwen/Qwen3.5-0.8B

Finetuned

ATH-MaaS/OvisOCR2

Quantized

(2)

this model

OvisOCR2 - GGUF Quantizations

Available Files

Main Text Models

Multimodal Projectors (mmproj)

Inference Guide (llama.cpp)

Basic Command Line Example

Model tree for Abiray/OvisOCR2-GGUF

Multimodal Projectors (`mmproj`)

Inference Guide (`llama.cpp`)