NEWVectors or files. Pick a path.Start →
    Models/Captioning/google/medgemma-27b-it
    HFScene CaptioningCustom (see model card)

    medgemma-27b-it

    by google

    Gemma-based vision-language model tuned for medical imaging and report generation

    Identifiers
    Model ID
    google/medgemma-27b-it
    Feature URI
    mixpeek://image_extractor@v1/medgemma_27b_it_v1

    Overview

    MedGemma 27B (instruction-tuned) is Google's medical adaptation of Gemma 3, taking image and text input and producing text. Its Hugging Face card tags the modalities it targets directly: x-ray, chest x-ray, pathology, dermatology, fundus, radiology report generation and medical embeddings.

    On Mixpeek it fits the same slot as a general VLM in a frames pipeline, with a domain vocabulary that a general model does not have. It is released under a custom licence rather than Apache, so read the terms before deploying it, particularly for anything clinical.

    Architecture

    Gemma 3 architecture, 27B parameters, instruction-tuned, image-text-to-text. Distributed as safetensors for transformers.

    Mixpeek SDK Integration

    import { Mixpeek } from "mixpeek";
    
    const mixpeek = new Mixpeek({ apiKey: process.env.MIXPEEK_API_KEY });
    
    await mixpeek.collections.create({
      collection_name: "imaging_studies",
      feature_extractors: [
        { extractor: "mixpeek://image_extractor@v1/medgemma_27b_it_v1" },
      ],
    });

    Capabilities

    • Radiology report generation from imaging studies
    • Visual question answering with medical vocabulary
    • Pathology, dermatology and fundus image description
    • Medical embeddings for domain retrieval

    Use Cases on Mixpeek

    Making an imaging archive searchable by finding rather than by filename
    Drafting structured descriptions for teaching and reference collections
    Domain-specific enrichment where a general VLM lacks the vocabulary
    Research retrieval across mixed imaging modalities

    Specification

    FrameworkHF
    Organizationgoogle
    FeatureScene Captioning
    Outputtext
    Modalitiesvideo, image
    RetrieverSemantic Search
    Parameters27B
    LicenseCustom (see model card)
    Downloads/mo267K

    Research Paper

    MedGemma 27B IT on Hugging Face

    arxiv.org

    Build a pipeline with medgemma-27b-it

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

    Run it on your own data, free