Instructions to use padeoe/granite-docling-258M-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use padeoe/granite-docling-258M-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 padeoe/granite-docling-258M-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf padeoe/granite-docling-258M-GGUF:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf padeoe/granite-docling-258M-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf padeoe/granite-docling-258M-GGUF:F16

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 padeoe/granite-docling-258M-GGUF:F16
# Run inference directly in the terminal:
./llama-cli -hf padeoe/granite-docling-258M-GGUF:F16

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 padeoe/granite-docling-258M-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf padeoe/granite-docling-258M-GGUF:F16

Use Docker

docker model run hf.co/padeoe/granite-docling-258M-GGUF:F16

LM Studio
Jan

vLLM

How to use padeoe/granite-docling-258M-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "padeoe/granite-docling-258M-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": "padeoe/granite-docling-258M-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/padeoe/granite-docling-258M-GGUF:F16

Ollama
How to use padeoe/granite-docling-258M-GGUF with Ollama:
```
ollama run hf.co/padeoe/granite-docling-258M-GGUF:F16
```

Unsloth Studio

How to use padeoe/granite-docling-258M-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 padeoe/granite-docling-258M-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 padeoe/granite-docling-258M-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for padeoe/granite-docling-258M-GGUF to start chatting

Docker Model Runner
How to use padeoe/granite-docling-258M-GGUF with Docker Model Runner:
```
docker model run hf.co/padeoe/granite-docling-258M-GGUF:F16
```

Lemonade

How to use padeoe/granite-docling-258M-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull padeoe/granite-docling-258M-GGUF:F16

Run and chat with the model

lemonade run user.granite-docling-258M-GGUF-F16

List all available models

lemonade list

Atomic Chat

Granite-Docling-258M-GGUF

GGUF format of ibm-granite/granite-docling-258M, a multimodal document OCR model that converts document images to Docling format.

Converted with llama.cpp.

Files

File	Quant	Size	Note
`granite-docling-258M-f16.gguf`	F16	317 MB	Full precision
`granite-docling-258M-q8_0.gguf`	Q8_0	170 MB	Recommended
`mmproj-granite-docling-258M-f16.gguf`	F16	182 MB	Vision encoder (required)

Usage

CLI

llama-mtmd-cli \
    --model granite-docling-258M-q8_0.gguf \
    --mmproj mmproj-granite-docling-258M-f16.gguf \
    --image document.png \
    --n-predict 4096 --ctx-size 8192 --temp 0.0 \
    -p "Convert this page to docling."

Server (OpenAI-compatible API)

llama-server \
    -m granite-docling-258M-q8_0.gguf \
    --mmproj mmproj-granite-docling-258M-f16.gguf \
    --ctx-size 8192 --special --jinja \
    --host 0.0.0.0 --port 8080

Benchmark (CPU only, Q8_0)

CPU	Config	Long text (4096 tok)	Short text (50 tok)
EPYC 9654 (96C)	192 inst x 1t	1.73 img/s	29.4 img/s
EPYC 9654 (16C)	16 inst x 1t	0.67 img/s	8.68 img/s

For this small model, 1 thread per instance with max instances = core count gives best throughput.

Downloads last month: 25

GGUF

Model size

0.2B params

Architecture

llama

Hardware compatibility

8-bit

16-bit

Model tree for padeoe/granite-docling-258M-GGUF

Base model

ibm-granite/granite-docling-258M

Quantized

(13)

this model