tiiuae/Falcon-OCR

Image To Text·tiiuae· 5.1K· 119

transformers apache-2.0 Image To Text 269.9M params arxiv:2603.27365license:apache-2.0

Falcon OCR is a 300M parameter early-fusion vision-language model for document OCR. Given an image, it can produce plain text, LaTeX for formulas, or HTML for tables, depending on the requested output format.

Open in MLForge Sign up free Desktop app Source ↗

# pull & run locally
pip install mlforge-sdk && mlforge pull tiiuae/Falcon-OCR

Model details

Task

Image To Text

Provider

tiiuae

Framework

transformers

Parameters

269.9M

Size

4.0 GB

License

apache-2.0

Downloads

5.1K

Likes

119

Paper

arXiv:2603.27365

Updated

2026-05-13

About tiiuae/Falcon-OCR

Related Image To Text

B Salesforce/blip-image-captioning-base Image To Text 1.9M 863 🤗 HF B Salesforce/blip-image-captioning-large Image To Text ·469.7M params 737.4K 1.5K 🤗 HF P PaddlePaddle/PP-OCRv5_server_det Image To Text 587.3K 73 🤗 HF N numind/NuExtract3 Image To Text ·4.5B params 520.7K 270 🤗 HF U PaddlePaddle/UVDoc Image To Text 512.8K 11 🤗 HF T microsoft/trocr-small-handwritten Image To Text 448.6K 63 🤗 HF

Browse all Image To Text models →