@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 one…

X AI KOLs Timeline Models

Summary

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.

| CHINA HAS ENDED THE OCR BUSINESS A 3 billion parameter model the size of a peanut can read a full 100-page PDF in one go. Without splitting pages. Without loss of context. Without a cloud bill. Meet Unlimited-OCR • Reads full documents with a 32K context window • 93% on standard OCR analysis benchmarks (+6 over the baseline) • Error rate stays below 0.11 even after 40+ pages • Multilingual out of the box • Runs 100% locally on your hardware • Supports Transformers, vLLM, SGLang, Docker, Ollama and llama.cpp Here's the crazy part: Most OCR tools still process documents page by page. Unlimited-OCR reads the entire document as a single context, preserving tables, references, layouts, and relationships between pages. That changes everything. Meanwhile, companies are paying: • $1.50–$15 per 1,000 pages • Sending sensitive PDFs to cloud providers • Waiting for API responses This model does it offline. Free. Forever. Built by Baidu to go beyond DeepSeek-OCR. It already has over 1.9 million downloads on Hugging Face... ...and almost nobody is talking about it yet. Open source moves faster than most enterprise software.
Original Article
View Cached Full Text

Cached at: 07/21/26, 06:39 AM

| CHINA HAS ENDED THE OCR BUSINESS

A 3 billion parameter model the size of a peanut can read a full 100-page PDF in one go.

Without splitting pages. Without loss of context. Without a cloud bill.

Meet Unlimited-OCR

• Reads full documents with a 32K context window • 93% on standard OCR analysis benchmarks (+6 over the baseline) • Error rate stays below 0.11 even after 40+ pages • Multilingual out of the box • Runs 100% locally on your hardware • Supports Transformers, vLLM, SGLang, Docker, Ollama and llama.cpp

Here’s the crazy part:

Most OCR tools still process documents page by page.

Unlimited-OCR reads the entire document as a single context, preserving tables, references, layouts, and relationships between pages.

That changes everything.

Meanwhile, companies are paying:

1.50–15 per 1,000 pages • Sending sensitive PDFs to cloud providers • Waiting for API responses

This model does it offline. Free. Forever.

Built by Baidu to go beyond DeepSeek-OCR.

It already has over 1.9 million downloads on Hugging Face…

…and almost nobody is talking about it yet.

Open source moves faster than most enterprise software.

Similar Articles

@CoderDaMing: China has open-sourced a peanut-sized OCR that can parse an entire 100-page PDF in one go. It's called 'Unlimited-OCR'. Only 3B parameters. Runs locally. Other OCR tools cut documents page by page, easily losing context. This one reads the entire document at once. → Single 'long-range' parse (32K context window...

X AI KOLs Timeline

China has open-sourced the OCR model Unlimited-OCR with only 3B parameters, which can parse an entire 100-page PDF in one go, supports local execution, achieves 93% accuracy, and is completely free and open-source.

baidu/Unlimited-OCR

Hugging Face Models Trending

Baidu releases Unlimited-OCR, a new model for one-shot long-horizon document parsing, building on Deepseek-OCR. It supports single image and multi-page/PDF parsing via Hugging Face Transformers and SGLang.