AtlasAI Center AI tool intelligence
PaddlePaddle · Open-weight model

PaddleOCR VL

PaddleOCR VL is a image-text-to-text model published on Hugging Face by PaddlePaddle.

Downloads (30d)
17,230
Released
Oct 16, 2025
Specifications

PaddleOCR VL specs

Provider
PaddlePaddle
Type
Open-weight model
Model ID
PaddlePaddle/PaddleOCR-VL
Task
image text to text
Released
Oct 16, 2025
License
apache-2.0
Architecture
PaddleOCR
Base model
baidu/ERNIE-4.5-0.3B-Paddle
Downloads
17,230Hugging Face, last 30 days
Likes
1,688
Languages
English, Chinese
Popularity
11/10017,230 Hugging Face downloads in the last 30 days
Source
Hugging Face
Overview

About PaddleOCR VL

PaddleOCR VL is an open-weight model from PaddlePaddle, released on Oct 16, 2025, with the apache-2.0 license, 17,230 Hugging Face downloads in the last 30 days.

Specs are sourced from Hugging Face and were last checked on Nov 20, 2026. Always confirm current pricing and limits with the provider before production use.

FAQ

PaddleOCR VL questions

When was PaddleOCR VL released?

PaddleOCR VL was published on Oct 16, 2025.

Can I run PaddleOCR VL locally?

PaddleOCR VL is published as an open-weight model on Hugging Face under the apache-2.0 license, so you can download the weights and run them on compatible hardware, subject to the license terms.