@DataScienceDojo: A Chinese company just open-sourced an πππ that fixes something most AI-powered OCR tools quietly struggle with: theβ¦
Summary
Unlimited-OCR, a new open-source OCR model from a Chinese company, solves the memory growth issue common in AI OCR tools by keeping memory usage flat regardless of document length, enabling single-pass reading of dozens of pages at 32K context. It's MIT-licensed, 3B parameters, multilingual, and already popular on GitHub.
View Cached Full Text
Cached at: 07/21/26, 08:38 AM
A Chinese company just open-sourced an πππ that fixes something most AI-powered OCR tools quietly struggle with: they slow down and get heavier on memory the longer the document gets.
Hereβs why that happens. Most of these models process a document by generating text one piece at a time, and they keep track of everything theyβve already read as they go.
The more pages you feed in, the more that memory builds up, so a 40-page file taxes the system a lot more than a 2-page one.
Unlimited-OCR changes how the model pays attention to what itβs read, so that memory stays flat no matter how many pages you throw at it. Thatβs what lets it read dozens of pages in π¨π§π π©ππ¬π¬, at a standard 32K context length, without splitting the document up and losing the thread between pages.
-
MIT licensed, 3B parameters
-
Multilingual out of the box
-
Works with Transformers and SGLang directly
-
Already at 6.7k stars on GitHub within days of release
If youβre running document parsing through Textract, Google Vision, or Azure Document Intelligence, this is worth testing locally. Itβs small enough to self-host, and Baidu says the same underlying technique should work for speech recognition and translation too, not just OCR.
#UnlimitedOCR #DeepSeekOCR #OpenSourceAI #LLMEngineering #DocumentAI #AIEngineering
Similar Articles
@thesupermanmx: China just open-sourced an OCR model that transcribes an entire book in a single pass. It's called Unlimited OCR. Builtβ¦
China open-sourced Unlimited OCR, an OCR model based on DeepSeek OCR that can transcribe entire books in a single pass with constant memory usage, achieving 93% on standard parsing benchmarks.
@BaiduAI_News: Weβre open-sourcing Unlimited OCR β built to read long documents in one pass. With 3B total parameters and only 500M acβ¦
Baidu open-sources Unlimited OCR, a 3B parameter model (500M activated) that reads long documents in a single pass using Reference Sliding Window Attention (R-SWA), achieving state-of-the-art results on OmniDocBench.
@S0N_IA: | CHINA HAS ENDED THE OCR BUSINESS A 3 billion parameter model the size of a peanut can read a full 100-page PDF in oneβ¦
Baidu releases Unlimited-OCR, a 3B parameter open-source model that reads full 100-page PDFs in one go with a 32K context window, achieving 93% accuracy and running locally. It has 1.9 million Hugging Face downloads but little mainstream attention.
@GoSailGlobal: Current OCR processes multi-page documents page by page. Every time you turn a page, memory is reset. Today, Baidu quietly open-sourced a model on GitHub and HuggingFace called Unlimited OCR, inspired by how humans copy books: - When copying a book, you don't reread hundreds of pages every time you write a word...
Baidu has open-sourced the Unlimited OCR model, which uses a Reference Sliding Window Attention (R-SWA) mechanism to parse documents up to 32K context in a single pass, eliminating the need for page-by-page inference.
Unlimited OCR: One-Shot Long-Horizon Parsing
Baidu releases Unlimited-OCR, an open-source model for one-shot long-horizon document parsing, building upon Deepseek-OCR with support for single images, multi-page documents, and PDFs.