Documents and OCR

DeepSeek-OCR

An OCR model that compresses a page into a small number of visual tokens, so it processes large volumes quickly. Version 2 better understands reading order.

Developer
DeepSeek, China
First release
Oct 2025
Latest release
Jan 2026
Sizes
about 3B
License
Commercial use allowedDeepSeek-OCR: MIT; DeepSeek-OCR 2: Apache 2.0
Russian
Not stated
Ready-made builds
GGUF, GPTQ, MLX (Apple)
Running
Available in OllamaNeeds a GPU
Industries
Documents and accounting, Finance
Deploy on your server Hugging Face GitHub

What it does

  • Bulk recognition of scanned invoices and contracts
  • Table recognition
  • Converting PDFs to Markdown for search and RAG

Where it is used

Document workflowAccountingArchives

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. DeepSeek-OCR 2
  2. DeepSeek-OCR

How to run it

With Ollama — the fastest wayInstall Ollama on your computer or server and find the model in its library by name. Good enough to try the model on your own tasks in one evening.Find it in the Ollama library
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 DeepSeek-OCR be used in a commercial project?

Yes. License: DeepSeek-OCR: MIT; DeepSeek-OCR 2: Apache 2.0. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does DeepSeek-OCR need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller 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 DeepSeek-OCR 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 DeepSeek-OCR and what does it cost?

The DeepSeek-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.

Comparisons

Similar models

Documents 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.

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.

DetailsDocuments and OCRGLM-OCRZhipu AI (Z.ai) · ChinaCommercial use allowed

A lightweight OCR model from Zhipu for document parsing. The model card lists Russian among supported languages; built for high load and low-end hardware.

Details

Source: huggingface.co/deepseek-ai/DeepSeek-OCR-2. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.