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
```

Granite-Docling-258M Variants, Docker and Inference Snippets Starting Point

#27

by daybytez - opened Sep 26, 2025

Discussion

daybytez

Sep 26, 2025

Granite-Docling-258M Variants Overview (Bytez Round-Up)

Variant	RAM / VRAM Needed	Notes (Usage)	Download (Formatted)	Run Instantly
Granite-Docling-258M (Base)	~8–12 GB (est., fp16)	Multimodal Image+Text→Text for doc conversion	HF safetensors	Bytez Docling
Granite-Docling-258M-MLX	~8–12 GB (est., fp16)	Optimized for Apple Silicon / MLX runtime	HF MLX	❓
Quantized (community, GGUF / GPTQ)	~2–6 GB (est., 4-bit / 8-bit)	Runs on consumer GPUs with lower memory	GGUF/GPTQ search	❓
Domain fine-tunes (planned)	~8–12 GB (est.)	Legal, finance, or scientific doc specializations	HF search	❓

Docker Quickstart

version: "3.8"
services:
  granite_docling:
    image: ghcr.io/bytez-com/models/ibm-granite/granite-docling-258m:latest
    ports:
      - "8080:80"

Run request:

docker compose up -d
curl -X POST http://localhost:8080/generate \
  -H "Content-Type: application/json" \
  -d '{"prompt":"Convert this PDF page into structured Markdown.","max_tokens":128}'

Bytez SDK Quickstart (Node.js)

npm i bytez.js
# or
yarn add bytez.js

import Bytez from "bytez.js"

const sdk = new Bytez("YOUR_API_KEY")
const model = sdk.model("ibm-granite/granite-docling-258M")

const { error, output } = await model.run(
  "Convert this scanned invoice into clean structured text."
)

console.log({ error, output })

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