Documents and OCR

SmolDocling и Granite-Docling

Tiny models for the open Docling document converter: they turn a page into markup with tables, formulas and code. Run on an ordinary laptop.

Developer
IBM and Hugging Face, USA
First release
Mar 2025
Latest release
Sep 2025
Sizes
256M – 258M
License
Commercial use allowedGranite-Docling: Apache 2.0; SmolDocling: CDLA-Permissive 2.0
Russian
Not supported
Running
On your own serverAlso runs without a GPU
Industries
Documents and accounting, Legal
Deploy on your server Hugging Face GitHub

What it does

  • Converting PDFs and scans to Markdown for search and RAG
  • Recognising tables in reports
  • Processing invoices and contracts on an ordinary PC

Where it is used

Document workflowLegal departmentsInternal knowledge bases

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
fits
1 GPUOne GPU with 16–80 GB — mid-size versions
no versions
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. Granite-Docling-258M
  2. SmolDocling-256M-preview

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems.

Frequently asked questions

Can SmolDocling и Granite-Docling be used in a commercial project?

Yes. License: Granite-Docling: Apache 2.0; SmolDocling: CDLA-Permissive 2.0. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does SmolDocling и Granite-Docling need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Some versions also run on an ordinary CPU, without a GPU. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does SmolDocling и Granite-Docling support Russian?

No. The model card lists its languages and Russian is not among them.

Where can I download SmolDocling и Granite-Docling and what does it cost?

The SmolDocling и Granite-Docling weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

Image + textGranite VisionIBM · USACommercial use allowed

Compact IBM models for business documents: tables, charts, forms, field-value pairs. The model card openly warns that it works best with English.

DetailsDocuments and OCRMinerUShanghai AI Laboratory (OpenDataLab) · ChinaCommercial use allowed

A popular open tool for converting PDFs to Markdown with its own small model. MinerU2.5-Pro was improved through data alone, without growing in size. Languages on the card: Chinese and English.

DetailsDocuments and OCRPaddleOCR-VLBaidu (PaddlePaddle) · ChinaCommercial use allowed

A compact document parsing model from the popular PaddleOCR toolkit. Per the model card it supports 109 languages, including Russian; version 1.6 leads the OmniDocBench benchmark.

Details

Source: huggingface.co/ibm-granite/granite-docling-258M. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.