NEWVectors or files. Pick a path.Start →
    Models/Video Classification/facebook/vjepa2-vith-fpc64-256
    Video Classificationtransformersmit

    vjepa2-vith-fpc64-256

    by facebook

    Identifier
    Model ID
    facebook/vjepa2-vith-fpc64-256

    Tags

    transformerssafetensorsvjepa2feature-extractionvideovideo-classificationlicense:mitendpoints_compatibleregion:us

    Use vjepa2-vith-fpc64-256 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, vjepa2-vith-fpc64-256 runs as a managed extractor inside a processing pipeline. Point a bucket of video 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.