---
title: PaddlePaddle/PaddleOCR-VL-1.5
description: "PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing. PaddleOCR-VL, 959M parameters."
canonical_url: https://superlinked.com/models/paddlepaddle-paddleocr-vl-1-5
last_updated: 2026-05-24
---

# PaddlePaddle/PaddleOCR-VL-1.5

PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing

Source: [PaddlePaddle/PaddleOCR-VL-1.5 on HuggingFace](https://huggingface.co/PaddlePaddle/PaddleOCR-VL-1.5)
Base model: [baidu/ERNIE-4.5-0.3B-Paddle](https://huggingface.co/baidu/ERNIE-4.5-0.3B-Paddle)

## Overview

| Field | Value |
|-------|-------|
| Architecture | PaddleOCR-VL |
| Parameters | 959M |
| Tasks | Extract |
| Outputs | Text (Markdown) |
| License | apache-2.0 |
| Inputs | image |
| Languages | en, zh, multilingual |

## Benchmarks

No benchmark results available for this model.