Documents and OCR

olmOCR

A model and toolkit for converting PDFs into clean text at scale, preserving reading order, tables and formulas. Built to process millions of pages.

Developer
Ai2 (Allen Institute for AI), USA
First release
Feb 2025
Latest release
Oct 2025
Sizes
7B
License
Commercial use allowedApache 2.0
Russian
Not supported
Ready-made builds
GGUF, GPTQ
Running
On your own serverNeeds a GPU
Industries
Documents and accounting, Science and research
Deploy on your server Hugging Face GitHub

What it does

  • Bulk digitisation of a PDF archive
  • Converting contracts and reports into text
  • Preparing documents for search and RAG
  • Table recognition

Where it is used

Document workflowLegal departmentsArchives and libraries

Hardware requirements

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

Versions

  1. olmOCR-2-7B-1025
  2. olmOCR-7B-0825
  3. olmOCR-7B-0725
  4. olmOCR-7B-0225-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. Quantization compresses a model so it takes less video memory and runs on more modest hardware. Answers change slightly, so quality is checked on your own examples.

Frequently asked questions

Can olmOCR be used in a commercial project?

Yes. License: Apache 2.0. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does olmOCR need?

At minimum: One GPU with 16–80 GB — mid-size versions. Without a GPU the model is not practical. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does olmOCR support Russian?

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

Where can I download olmOCR and what does it cost?

The olmOCR 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

Documents 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 OCRChandra OCRDatalab · USACommercial use with conditions

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 OCRdots.ocrrednote hilab (Xiaohongshu) · ChinaCommercial use allowed

A multilingual document parsing model: text, tables, formulas and reading order in one pass. dots.mocr also turns charts and diagrams into vector SVG.

Details

Source: huggingface.co/allenai/olmOCR-2-7B-1025. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.