NEWWhy single embeddings fail for video.Read the post →
    Models/Captioning/google/gemma-4-4b-it
    HFScene Captioning

    gemma-4-4b-it

    by google

    1.9Mdl/month
    HuggingFaceUse in Pipeline
    Identifiers
    Model ID
    google/gemma-4-4b-it
    Feature URI
    mixpeek://image_extractor@v1/google_gemma4_4b_v1

    Specification

    FrameworkHF
    Organizationgoogle
    FeatureScene Captioning
    Outputtext
    Modalitiesvideo, image
    RetrieverSemantic Search
    Downloads/mo1.9M

    Build a pipeline with gemma-4-4b-it

    Add this model to a processing pipeline alongside other extractors. Combine with retrieval stages for end-to-end search.

    Open Pipeline Builder

    Alternative Models

    Salesforce/blip2-opt-2.7b
    Scene Captioning
    microsoft/Florence-2-large
    Scene Captioning
    google/paligemma2-3b-mix-448
    Scene Captioning
    Qwen/Qwen3-VL-8B-Instruct
    Scene Captioning