NEWVectors or files. Pick a path.Start →
    Models/Document Analysis/PaddlePaddle/PP-DocLayoutV3
    HFDocument Structure

    PP-DocLayoutV3

    by PaddlePaddle

    400Kdl/month
    HuggingFaceUse in Pipeline
    Identifiers
    Model ID
    PaddlePaddle/PP-DocLayoutV3
    Feature URI
    mixpeek://document_extractor@v1/paddle_pp_doclayoutv3_v1

    Explore on Mixpeek

    More Document Analysis models

    Compare alternatives in this category

    Best Document AI Platforms

    Hand-picked tools & platforms compared

    OCR & Document AI Internals

    Deep-dive technical guide

    Feature Extractors

    See how Mixpeek runs models as extractors

    Mixpeek Vector Store

    Store & search embeddings at scale

    Pricing

    Usage-based pricing for pipelines

    All Curated Lists

    Compare models, APIs & infrastructure

    Specification

    FrameworkHF
    OrganizationPaddlePaddle
    FeatureDocument Structure
    Outputstructure tokens
    Modalitiesdocument
    RetrieverSection Filter
    Downloads/mo400K

    Build a pipeline with PP-DocLayoutV3

    Add this model to a processing pipeline alongside other extractors. Combine with retrieval stages for end-to-end search.

    Open Studio

    Alternative Models

    microsoft/layoutlmv3-base
    Document Structure
    naver-clova-ix/donut-base
    Document Structure
    ibm-granite/granite-docling-258M
    Document Structure
    fastino/gliner2-base-v1
    Document Structure

    Related in Document Analysis

    microsoft/table-transformer-detection
    Table Extraction
    microsoft/table-transformer-structure-recognition-v1.1-all
    Table Extraction
    poloclub/UniTable
    Table Extraction
    microsoft/table-transformer-structure-recognition-v1.1-pub
    Table Extraction