PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model
Paper • 2510.14528 • Published • 129
- OCR - Optical Character Recognition
-
-
deepseek-ai/DeepSeek-OCR
Image-Text-to-Text • 3B • Updated • 2.25M • 3.34k -
PaddlePaddle/PaddleOCR-VL
Image-Text-to-Text • 1.0B • Updated • 12.3k • 1.64k -
nanonets/Nanonets-OCR2-3B
Image-Text-to-Text • 4B • Updated • 529k • 514 -
lvyufeng/PaddleOCR-VL-0.9B
Image-Text-to-Text • 1.0B • Updated • 2.03k • 5 -
dots-studio/dots.ocr
Image-Text-to-Text • 3B • Updated • 310k • 1.32k -
bartowski/allenai_olmOCR-2-7B-1025-GGUF
Image-Text-to-Text • 8B • Updated • 1.44k • 5 -
tencent/HunyuanOCR
Image-Text-to-Text • 1B • Updated • 447k • 798 -
lightonai/LightOnOCR-1B-1025
Image-to-Text • 1B • Updated • 134k • 256 -
deepseek-ai/DeepSeek-OCR-2
Image-Text-to-Text • 3B • Updated • 1.45M • 1.08k -
lightonai/LightOnOCR-2-1B
Image-Text-to-Text • 1B • Updated • 633k • 793 -
zai-org/GLM-OCR
Image-Text-to-Text • 1B • Updated • 3.25M • • 1.98k -
qualcomm/EasyOCR
Image-to-Text • Updated • 191 • 41 -
baidu/Qianfan-OCR
Image-Text-to-Text • 5B • Updated • 194k • 1.2k -
DianJin/DianJin-OCR-R1
Updated • 12 -
nvidia/nemotron-ocr-v2
Image-to-Text • Updated • 1.2k • 244 -
ATH-MaaS/OvisOCR
Image-Text-to-Text • 1B • Updated • 564 • 16 -
baidu/Unlimited-OCR
Image-Text-to-Text • 3B • Updated • 2.94M • 4.05k -
tiiuae/Falcon-OCR
Image-to-Text • 0.3B • Updated • 3.25k • 136