Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Story

Open-source OCR models cut million-page digitization cost

AI summary

Daniel van Strien of Hugging Face benchmarked eight open-source AI OCR models on 850 pages of historical books and archival documents using the same Nvidia RTX PRO 6000 GPU. At equal image sizes, RolmOCR cost about $0.51 per 1,000 pages, while LightOnOCR-3-0.8B cost just under $0.10, putting GPU rental for one million pages at $65 to $130 depending on the material. The newest model was at least as accurate as the oldest on book pages, though some models hallucinated text on blank pages or repeatedly produced the same content.

In-depth insight

The benchmark provides a practical cost comparison for large-scale AI document digitization while identifying accuracy and reliability issues that operators still need to check.

OCR models now digitize a million pages for under $130 as costs drop fivefold in 18 months

Jonathan Kemper View the LinkedIn Profile of Jonathan Kemper

Nov 19, 2026

Pulling text out of scanned books and records has gotten a lot cheaper with freely available AI models. Daniel van Strien of Hugging Face compared eight such models that recognize text in images. He tested them on 850 pages from old natural history books, the 1771 Encyclopaedia Britannica, and typed and printed archival documents. All models ran on the same GPU, an Nvidia RTX PRO 6000 that van Strien rented through Hugging Face for $2.75 per hour. At the same image size, the oldest model from April 2025 (RolmOCR) cost about 51 cents per 1,000 pages. The newest from October 2026 (LightOnOCR-3-0.8B) came in at just under 10 cents. A million pages now runs between $65 and $130 in GPU rental, depending on the source material.

According to van Strien, optimizing how the models ran saved about as much money as switching to newer models did, if not more. That meant feeding pages more evenly, using smaller scans, updating software, and running a faster GPU. The newest model read book pages at least as accurately as the oldest one. Some models, though, hallucinated text on blank pages or repeated the same content over and over.

#Hugging Face#RolmOCR#LightOnOCR-3-0.8B#Nvidia#Nvidia RTX PRO 6000

Original · 1 min readRead the original
Group chat

No comments yet. Start the conversation.