NEWVectors or files. Pick a path.Start →
    Models/Zero Shot Image Classification/facebook/metaclip-2-worldwide-s16
    Zero Shot Image Classificationtransformerscc-by-nc-4.0

    metaclip-2-worldwide-s16

    by facebook

    Identifier
    Model ID
    facebook/metaclip-2-worldwide-s16

    Tags

    transformerssafetensorsmetaclip_2zero-shot-image-classificationclipmultilingualarxiv:2507.22062license:cc-by-nc-4.0endpoints_compatibleregion:us

    Use metaclip-2-worldwide-s16 on Mixpeek

    Build multimodal processing pipelines with this model and others. Extract features, run inference, and set up retrieval in Mixpeek Studio.

    Open Studio

    How It Runs on Mixpeek

    On Mixpeek, metaclip-2-worldwide-s16 runs as a managed extractor inside a processing pipeline. Point a bucket of zero shot image classification data at it, and Mixpeek handles GPU provisioning, batching, retries, and writing the outputs into a vector store you can query.

    Extractor outputs land in the Mixpeek Vector Store (MVS), where you can combine them with retrieval, reranking, and filter stages to build end-to-end search and agent-perception pipelines, no model-serving infrastructure to maintain.