NEWAgents can now see video via MCP.Try it now →
    Models/Image Feature Extraction/canvit/canvitb16-add-vpe-pretrain-g128px-s512px-in21k-dv3b16-2026-02-02-mlx
    Image Feature Extractionmlxmit

    canvitb16-add-vpe-pretrain-g128px-s512px-in21k-dv3b16-2026-02-02-mlx

    by canvit

    49dl/month
    HuggingFaceUse in Pipeline
    Identifier
    Model ID
    canvit/canvitb16-add-vpe-pretrain-g128px-s512px-in21k-dv3b16-2026-02-02-mlx

    Tags

    mlxsafetensorsvisionapple-siliconcanvitactive-visionimage-feature-extractionarxiv:2603.22570license:mitregion:us

    Use canvitb16-add-vpe-pretrain-g128px-s512px-in21k-dv3b16-2026-02-02-mlx 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

    Organizationcanvit
    TaskImage Feature Extraction
    Librarymlx
    Licensemit
    Downloads/mo49

    View on HuggingFace

    See model card, files, and community discussion

    Related Image Feature Extraction Models

    timm/vit_base_patch14_dinov2.lvd142m
    4.8M
    google/vit-base-patch16-224-in21k
    4.2M
    facebook/dinov2-small
    2.4M
    facebook/dinov2-base
    2.2M
    facebook/dinov2-large
    1.7M
    facebook/dinov3-vitb16-pretrain-lvd1689m
    1.3M
    facebook/dinov3-vitl16-pretrain-lvd1689m
    698K
    timm/vit_small_patch14_reg4_dinov2.lvd142m
    547K