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

Libraries

How to use ibm-granite/granite-docling-258M with Transformers:

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

pipe = pipeline("image-text-to-text", model="ibm-granite/granite-docling-258M")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("ibm-granite/granite-docling-258M")
model = AutoModelForMultimodalLM.from_pretrained("ibm-granite/granite-docling-258M", device_map="auto")
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?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ibm-granite/granite-docling-258M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ibm-granite/granite-docling-258M",
		"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/ibm-granite/granite-docling-258M

SGLang

How to use ibm-granite/granite-docling-258M 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 "ibm-granite/granite-docling-258M" \
    --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": "ibm-granite/granite-docling-258M",
		"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 "ibm-granite/granite-docling-258M" \
        --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": "ibm-granite/granite-docling-258M",
		"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"
						}
					}
				]
			}
		]
	}'

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

having trouble with efficiency/speed

#35

by hammertime23 - opened Oct 3, 2025

Discussion

hammertime23

Oct 3, 2025

took 6 minutes to do an extraction of a simple pdf.... also thought it would handle images better with better captioning and whatnot. wondering what i am doing wrong if someone can help. i can only upload images here... but happy to share the pdf with anyone who cares. i have an rtx 5090 i'm running it with... and it took 6 minutes for this pdf https://papers.ssrn.com/sol3/papers.cfm?abstract_id=5056871 (ml) PS C:\Users\xxxxxxxxx> docling --to md --pipeline vlm --vlm-model granite_docling -v $pdf_path --output "C:\Users\xxxxxxx\Documents\Python Scripts\docling_test\out"
2025-10-02 21:11:31,049 - INFO - Loading plugin 'docling_defaults'
2025-10-02 21:11:31,051 - INFO - Registered ocr engines: ['easyocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract']
2025-10-02 21:11:31,060 - INFO - paths: [WindowsPath('C:/tmp/tmphx7vtdt2/ssrn-5056871.pdf')]
2025-10-02 21:11:31,069 - INFO - detected formats: [<InputFormat.PDF: 'pdf'>]
2025-10-02 21:11:31,100 - INFO - Going to convert document batch...
2025-10-02 21:11:31,100 - INFO - Initializing pipeline for VlmPipeline with options hash 14b35a24912cc09d5c7735b8ff9d88c1
2025-10-02 21:11:31,111 - INFO - Loading plugin 'docling_defaults'
2025-10-02 21:11:31,111 - INFO - Registered picture descriptions: ['vlm', 'api']
2025-10-02 21:11:31,128 - INFO - Accelerator device: 'cuda:0'
2025-10-02 21:11:32,998 - INFO - Processing document ssrn-5056871.pdf
2025-10-02 21:18:10,215 - INFO - Finished converting document ssrn-5056871.pdf in 399.16 sec.
2025-10-02 21:18:10,215 - INFO - writing Markdown output to C:\Users\ishan\Documents\Python Scripts\docling_test\out\ssrn-5056871.md
2025-10-02 21:18:10,231 - INFO - Processed 1 docs, of which 0 failed
2025-10-02 21:18:10,235 - INFO - All documents were converted in 399.17 seconds.

tiagobraga

Oct 7, 2025

We have also this problem performance, would be big help if has a fix or solution

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment