PaddleOCR-VL

unsloth/PaddleOCR-VL

Image Text to Text959M parametersPaddleOCRLicense: apache-2.0
Tracked by OpenModelStats since September 26, 2026View on Hugging Face ↗
Downloads 30D
103
Total downloads
1,264
Gained 7D
—
Gained 30D
—
Likes
18
Rank · tracked models
#53,517
374(down 374 places)this week
Parameters
959M
Last source update
Dec 9, 2025
  • It moved from #4880 to #4920 among tracked Image Text to Text models this week.

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

PaddleOCR-VL is a image text to text model published by unsloth. OpenModelStats has tracked the model since Sep 26, 2026, most recently observing it Oct 3, 2026.

Published
Dec 9, 2025
Last updated
Dec 9, 2025
Library
PaddleOCR
License
apache-2.0
Task
Image Text to Text
Parameters
958,588,736
Spaces
—
Derivative models
—
Velocity 7D/day
—
PaddleOCRsafetensorspaddleocr_vlERNIE4.5PaddlePaddleimage-to-textocrdocument-parselayouttableformulachart

Publisher

unslothView publisher statistics →

Derived from baidu/ERNIE-4.5-0.3B-Paddle (reported by the source; parent not yet tracked).

Similar models

Models similar to PaddleOCR-VL
ModelDL 30D
PaddleOCR-VL-1.6PaddlePaddle45.8K
PaddleOCR-VL-1.5PaddlePaddle17.4K
PaddleOCR-VLPaddlePaddle7,729
SenOCR-ViVietAlphaLabs1,112
PaddleOCR-VL-For-Mangajzhang533817
PaddleOCR-VL-0.9Blvyufeng370
unsloth/PaddleOCR-VL — Downloads, Growth & Stats | OpenModelStats