Documents and OCR

Surya OCR

A compact OCR toolkit from the makers of Marker and Chandra: text recognition, page layout, reading order and tables. Surya OCR 2 (650M) also runs on a CPU; Russian scored 88.8% in benchmarks.

Developer
Datalab, USA
First release
Feb 2024
Latest release
Jul 2026
Sizes
up to 650M
License
Commercial use with conditionsCode Apache 2.0; weights under a modified AI Pubs OpenRAIL-M: free for research, personal use and companies with revenue and funding up to $5 million, a paid license for everyone else. Early 2024 weights are CC BY-NC-SA
Russian
Supported
Running
On your own serverAlso runs without a GPU
Industries
Documents and accounting, Finance, Legal

What it does

  • Recognizing scans and PDFs, including in Russian
  • Page layout: headings, tables, images, reading order
  • Recognizing tables by rows and columns
  • Batch processing of large archives on your own server

Where it is used

Document managementAccountingArchives and librariesLegal departments

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. Surya Layout 2
  2. Surya OCR 2 (650M, одна модель на всё)
  3. Распознавание v2 и таблицы
  4. Макет и порядок чтения
  5. Surya (детекция и распознавание)

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 Surya OCR be used in a commercial project?

With conditions. License: Code Apache 2.0; weights under a modified AI Pubs OpenRAIL-M: free for research, personal use and companies with revenue and funding up to $5 million, a paid license for everyone else. Early 2024 weights are CC BY-NC-SA. Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.

What hardware does Surya OCR 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 Surya OCR support Russian?

Yes, Russian is listed on the model card.

Where can I download Surya OCR and what does it cost?

The Surya OCR 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

Source: huggingface.co/datalab-to/surya-ocr-2. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.