Indra OCR
A tiny OCR model that runs on an ordinary CPU with no graphics card and no PyTorch: it uses ONNX Runtime, takes about 230 ms per page on four cores and reads up to 49 pages per second. It turns PDFs and images into markdown, plain text or JSON with boxes for lines and blocks (headings, lists, tables, captions) and reading order. In digital PDFs it takes the existing text layer and recognises only what is missing. Russian is among the stated languages. For handwriting, formulas and complex tables the authors point to their larger Chandra. The speed and accuracy figures are the authors' own.
- Developer
- Datalab, USA
- First release
- Oct 2026
- Latest release
- Oct 2026
- Sizes
- about 1M parameters (the models weigh about 18 MB)
- License
- Commercial use with conditionsCode: Apache 2.0. Weights: a modified OpenRAIL-M, free for research, personal use and startups under 20 million dollars in funding or revenue, no competing with their API; everyone else needs a paid license
- Russian
- Supported
- Running
- On your own serverAlso runs without a GPU
- Industries
- Documents and accounting, Finance, Legal
What it does
- fast bulk conversion of PDFs and scans to markdown on a server with no graphics card
- search over document archives: text with boxes and reading order
- pre-marking pages before a heavy model
Where it is used
Hardware requirements
Versions
- Indra OCR
How to run it
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 Indra OCR be used in a commercial project?
With conditions. License: Code: Apache 2.0. Weights: a modified OpenRAIL-M, free for research, personal use and startups under 20 million dollars in funding or revenue, no competing with their API; everyone else needs a paid license. Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.
What hardware does Indra 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 Indra OCR support Russian?
Yes, Russian is listed on the model card.
Where can I download Indra OCR and what does it cost?
The Indra 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
- SelectionI pick the model size for your task and hardware and test it on your examples.
- DeploymentI deploy it on your server or in a closed network and provide an API.
- Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
- IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.
Similar models
A strong OCR model from the authors of Marker and Surya: handwriting, forms, tables. Per the model card it supports 90+ languages, with Russian among the examples.
DetailsDocuments and OCRPP-OCR и PP-DocLayout (классический PaddleOCR)Baidu (PaddlePaddle) · ChinaCommercial use allowedClassic lightweight PaddleOCR models: detecting and recognizing lines of text plus page layout. They run on CPUs and phones; there is a separate model for East Slavic languages, including Russian.
DetailsDocuments and OCRolmOCRAi2 (Allen Institute for AI) · USACommercial use allowedA model and toolkit for converting PDFs into clean text at scale, preserving reading order, tables and formulas. Built to process millions of pages.
DetailsSource: huggingface.co/datalab-to/indra-ocr. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.