NEWAgents can now see video via MCP.Try it now →
    Models/Image Text To Text/docling-project/SmolDocling-256M-preview
    Image Text To Texttransformerscdla-permissive-2.0

    SmolDocling-256M-preview

    by docling-project

    38Kdl/month
    1,614likes
    HuggingFaceUse in Pipeline
    Identifier
    Model ID
    docling-project/SmolDocling-256M-preview

    Tags

    transformersonnxsafetensorsidefics3image-text-to-textconversationalendataset:ds4sd/SynthCodeNetdataset:ds4sd/SynthFormulaNetdataset:ds4sd/SynthChartNetdataset:HuggingFaceM4/DoclingMatixarxiv:2503.11576arxiv:2305.03393base_model:HuggingFaceTB/SmolVLM-256M-Instructbase_model:quantized:HuggingFaceTB/SmolVLM-256M-Instructlicense:cdla-permissive-2.0endpoints_compatibleregion:us

    Use SmolDocling-256M-preview on Mixpeek

    Build multimodal processing pipelines with this model and others. Extract features, run inference, and set up retrieval, all through the Mixpeek pipeline builder.

    Open Pipeline Builder

    Specification

    Organizationdocling-project
    TaskImage Text To Text
    Librarytransformers
    Licensecdla-permissive-2.0
    Downloads/mo38K
    Likes1,614

    View on HuggingFace

    See model card, files, and community discussion

    Related Image Text To Text Models

    Qwen/Qwen3-VL-2B-Instruct
    141.1M
    Qwen/Qwen2.5-VL-7B-Instruct
    8.9M
    Qwen/Qwen3.5-9B
    7.2M
    google/gemma-4-31B-it
    6.0M
    google/gemma-4-26B-A4B-it
    4.5M
    moonshotai/Kimi-K2.5
    4.4M
    Qwen/Qwen3-VL-8B-Instruct
    4.0M
    Qwen/Qwen2-VL-2B-Instruct
    3.8M