Instructions to use prithivMLmods/Nanonets-OCR2-3B-AIO-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/Nanonets-OCR2-3B-AIO-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="prithivMLmods/Nanonets-OCR2-3B-AIO-GGUF")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("prithivMLmods/Nanonets-OCR2-3B-AIO-GGUF", dtype="auto")

llama-cpp-python

How to use prithivMLmods/Nanonets-OCR2-3B-AIO-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="prithivMLmods/Nanonets-OCR2-3B-AIO-GGUF",
	filename="Nanonets-OCR2-3B.IQ4_XS.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

llama.cpp

How to use prithivMLmods/Nanonets-OCR2-3B-AIO-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf prithivMLmods/Nanonets-OCR2-3B-AIO-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf prithivMLmods/Nanonets-OCR2-3B-AIO-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf prithivMLmods/Nanonets-OCR2-3B-AIO-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf prithivMLmods/Nanonets-OCR2-3B-AIO-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 prithivMLmods/Nanonets-OCR2-3B-AIO-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf prithivMLmods/Nanonets-OCR2-3B-AIO-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 prithivMLmods/Nanonets-OCR2-3B-AIO-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf prithivMLmods/Nanonets-OCR2-3B-AIO-GGUF:Q4_K_M

Use Docker

docker model run hf.co/prithivMLmods/Nanonets-OCR2-3B-AIO-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use prithivMLmods/Nanonets-OCR2-3B-AIO-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prithivMLmods/Nanonets-OCR2-3B-AIO-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": "prithivMLmods/Nanonets-OCR2-3B-AIO-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/prithivMLmods/Nanonets-OCR2-3B-AIO-GGUF:Q4_K_M

SGLang

How to use prithivMLmods/Nanonets-OCR2-3B-AIO-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "prithivMLmods/Nanonets-OCR2-3B-AIO-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/Nanonets-OCR2-3B-AIO-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 images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "prithivMLmods/Nanonets-OCR2-3B-AIO-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/Nanonets-OCR2-3B-AIO-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"
						}
					}
				]
			}
		]
	}'

Ollama
How to use prithivMLmods/Nanonets-OCR2-3B-AIO-GGUF with Ollama:
```
ollama run hf.co/prithivMLmods/Nanonets-OCR2-3B-AIO-GGUF:Q4_K_M
```

Unsloth Studio new

How to use prithivMLmods/Nanonets-OCR2-3B-AIO-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 prithivMLmods/Nanonets-OCR2-3B-AIO-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 prithivMLmods/Nanonets-OCR2-3B-AIO-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for prithivMLmods/Nanonets-OCR2-3B-AIO-GGUF to start chatting

Docker Model Runner
How to use prithivMLmods/Nanonets-OCR2-3B-AIO-GGUF with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/Nanonets-OCR2-3B-AIO-GGUF:Q4_K_M
```

Lemonade

How to use prithivMLmods/Nanonets-OCR2-3B-AIO-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull prithivMLmods/Nanonets-OCR2-3B-AIO-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Nanonets-OCR2-3B-AIO-GGUF-Q4_K_M

List all available models

lemonade list

Nanonets-OCR2-3B-AIO-GGUF

The Nanonets-OCR2-3B model is a state-of-the-art multimodal OCR and document understanding model based on the Qwen2.5-VL-3B architecture, fine-tuned for advanced image-to-markdown conversion with intelligent content recognition and semantic tagging. It can extract and transform complex document elements including text, tables (in markdown and HTML), LaTeX equations, flowcharts (as mermaid code), signatures, watermarks, checkboxes, and handwritten documents across multiple languages, supporting structured and context-rich outputs ideal for downstream AI processing. The model is 8-bit quantized for efficient inference, has about 3 billion parameters, a large 125K token context window, and supports visual question answering by providing direct answers from documents where applicable. Its design enhances document digitization workflows by unlocking structured data from unstructured documents, making it valuable in legal, medical, financial, and technical domains where accurate semantic extraction is crucial.

Model Files

File Name	Quant Type	File Size
Nanonets-OCR2-3B.f16.gguf	F16	6.18 GB
Nanonets-OCR2-3B.Q2_K.gguf	Q2_K	1.27 GB
Nanonets-OCR2-3B.Q3_K_L.gguf	Q3_K_L	1.71 GB
Nanonets-OCR2-3B.Q3_K_M.gguf	Q3_K_M	1.59 GB
Nanonets-OCR2-3B.Q3_K_S.gguf	Q3_K_S	1.45 GB
Nanonets-OCR2-3B.Q4_K_M.gguf	Q4_K_M	1.93 GB
Nanonets-OCR2-3B.Q4_K_S.gguf	Q4_K_S	1.83 GB
Nanonets-OCR2-3B.Q5_K_M.gguf	Q5_K_M	2.22 GB
Nanonets-OCR2-3B.Q5_K_S.gguf	Q5_K_S	2.17 GB
Nanonets-OCR2-3B.Q6_K.gguf	Q6_K	2.54 GB
Nanonets-OCR2-3B.Q8_0.gguf	Q8_0	3.29 GB
Nanonets-OCR2-3B.IQ4_XS.gguf	IQ4_XS	1.75 GB
Nanonets-OCR2-3B.i1-IQ1_M.gguf	i1-IQ1_M	850 MB
Nanonets-OCR2-3B.i1-IQ1_S.gguf	i1-IQ1_S	791 MB
Nanonets-OCR2-3B.i1-IQ2_M.gguf	i1-IQ2_M	1.14 GB
Nanonets-OCR2-3B.i1-IQ2_S.gguf	i1-IQ2_S	1.06 GB
Nanonets-OCR2-3B.i1-IQ2_XS.gguf	i1-IQ2_XS	1.03 GB
Nanonets-OCR2-3B.i1-IQ2_XXS.gguf	i1-IQ2_XXS	948 MB
Nanonets-OCR2-3B.i1-IQ3_M.gguf	i1-IQ3_M	1.49 GB
Nanonets-OCR2-3B.i1-IQ3_S.gguf	i1-IQ3_S	1.46 GB
Nanonets-OCR2-3B.i1-IQ3_XS.gguf	i1-IQ3_XS	1.39 GB
Nanonets-OCR2-3B.i1-IQ3_XXS.gguf	i1-IQ3_XXS	1.28 GB
Nanonets-OCR2-3B.i1-IQ4_NL.gguf	i1-IQ4_NL	1.83 GB
Nanonets-OCR2-3B.i1-IQ4_XS.gguf	i1-IQ4_XS	1.74 GB
Nanonets-OCR2-3B.i1-Q2_K.gguf	i1-Q2_K	1.27 GB
Nanonets-OCR2-3B.i1-Q2_K_S.gguf	i1-Q2_K_S	1.2 GB
Nanonets-OCR2-3B.i1-Q3_K_L.gguf	i1-Q3_K_L	1.71 GB
Nanonets-OCR2-3B.i1-Q3_K_M.gguf	i1-Q3_K_M	1.59 GB
Nanonets-OCR2-3B.i1-Q3_K_S.gguf	i1-Q3_K_S	1.45 GB
Nanonets-OCR2-3B.i1-Q4_0.gguf	i1-Q4_0	1.83 GB
Nanonets-OCR2-3B.i1-Q4_1.gguf	i1-Q4_1	2 GB
Nanonets-OCR2-3B.i1-Q4_K_M.gguf	i1-Q4_K_M	1.93 GB
Nanonets-OCR2-3B.i1-Q4_K_S.gguf	i1-Q4_K_S	1.83 GB
Nanonets-OCR2-3B.i1-Q5_K_M.gguf	i1-Q5_K_M	2.22 GB
Nanonets-OCR2-3B.i1-Q5_K_S.gguf	i1-Q5_K_S	2.17 GB
Nanonets-OCR2-3B.i1-Q6_K.gguf	i1-Q6_K	2.54 GB
Nanonets-OCR2-3B.imatrix.gguf	imatrix	3.39 MB
Nanonets-OCR2-3B.mmproj-Q8_0.gguf	mmproj-Q8_0	848 MB
Nanonets-OCR2-3B.mmproj-f16.gguf	mmproj-f16	1.34 GB