this is what open-source looks like
Baidu Inc.@Baidu_Inc
3B total parameters & 500M activated, yet powerful enough to transcribe 40+ pages in one pass while keeping context intact. Meet Unlimited OCR!
8:40 AM · Jun 23, 2026 · 47.8K Views
Baidu open-sources Unlimited-OCR, a 3B-parameter model that parses 40-page PDFs with a constant KV cache
The model achieved state-of-the-art performance on OmniDocBench.
219406238778.5K
Sentiment
Users are excited about Baidu's Unlimited OCR model because of its self-hosting potential as a cheaper alternative to APIs along with strong advantages for reducing errors in large document and archive transcription.
Pos
100.0%
Neg
0.0%
4 comments with sentiment.
Cluster Engagement
Digg Deeper
No Digg Deeper questions have been answered for this story yet.
Related links
