NEWWhy single embeddings fail for video.Read the post →
    Models/Image Feature Extraction/mlx-vision/vit_base_patch16_224.dinov3-mlxim
    Image Feature Extractionmlx-imageother

    vit_base_patch16_224.dinov3-mlxim

    by mlx-vision

    41dl/month
    HuggingFaceUse in Pipeline
    Identifier
    Model ID
    mlx-vision/vit_base_patch16_224.dinov3-mlxim

    Tags

    mlx-imagesafetensorsmlxvisiondinov3image-feature-extractionarxiv:2010.11929arxiv:2508.10104license:otherregion:us

    Use vit_base_patch16_224.dinov3-mlxim 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

    Organizationmlx-vision
    TaskImage Feature Extraction
    Librarymlx-image
    Licenseother
    Downloads/mo41

    View on HuggingFace

    See model card, files, and community discussion

    Related Image Feature Extraction Models

    google/vit-base-patch16-224-in21k
    3.4M
    timm/vit_base_patch14_dinov2.lvd142m
    3.2M
    facebook/dinov2-large
    2.9M
    facebook/dinov2-base
    2.9M
    facebook/dinov2-small
    2.4M
    facebook/dinov3-vitb16-pretrain-lvd1689m
    898K
    facebook/dinov3-vitl16-pretrain-lvd1689m
    683K
    timm/vit_small_patch14_reg4_dinov2.lvd142m
    642K