Documents and OCRImage + text

Donut

Reads a scanned document and returns a filled-in field structure straight away, with no separate OCR step. In HR it is fine-tuned for parsing resumes and forms. A human makes the decision about a candidate; automatic screening without review must not be used.

The last open version came out in Jul 2022. The family has not been updated for a long time: the model still works, but do not expect fixes or new sizes.

Developer
NAVER CLOVA, South Korea
First release
Jul 2022
Latest release
Jul 2022
Sizes
about 200M
License
Commercial use allowedMIT
Russian
Not stated
Running
On your own serverAlso runs without a GPU
Industries
Documents and accounting, HR, Finance
Deploy on your server Hugging Face GitHub

What it does

  • Extracting fields from forms and resumes
  • Parsing scans of certificates and diplomas
  • Detecting the type of an incoming document

Where it is used

HR and recruitingDocument workflowsAccounting

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
fits
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. donut-base-finetuned-rvlcdip, типы документов
  2. donut-base-finetuned-docvqa, вопросы к документу
  3. donut-base-finetuned-cord-v2, чеки
  4. donut-base

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 Donut be used in a commercial project?

Yes. License: MIT. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does Donut 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 Donut support Russian?

The model card does not list languages, so Russian support cannot be promised — it has to be tested on your own examples.

Where can I download Donut and what does it cost?

The Donut 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

Text analysisNuExtractNuMind · FranceCommercial use allowed

Models for template-based data extraction: give it a document or scan and a JSON field template, get a filled-in JSON back. NuExtract3 (4B) also converts scans to Markdown.

DetailsText analysisLayoutLM (v1–v3, LayoutXLM)Microsoft · USACommercial use with conditions

Classic document understanding models: they take into account the text, its position on the page and the image. They are fine-tuned to extract fields from forms and receipts. Only the first version is free for commercial use.

DetailsDocuments and OCRTrOCRMicrosoft · USACommercial use allowed

Recognizes a single line of text, including handwriting. The official weights are English only, but the model is often fine-tuned for other languages; there are community Russian versions.

Details

Source: huggingface.co/naver-clova-ix/donut-base. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.