Models / Google
Chat
Code
Vision

Gemma 3 12B

Lightweight Gemma 3 model with 128K context, vision-language input, and multilingual support for on-device AI.

About model

Gemma 3 12B generates human-like text based on input prompts, excelling at conversational dialogue and language understanding, suitable for developers and researchers requiring advanced natural language processing capabilities.

To run this model, you first need to deploy it on a Dedicated Endpoint.

    Related models
    • Model provider
      Google
    • Type
      Chat
      Code
      Vision
    • Main use cases
      Chat
      Vision
    • Fine tuning
      Supported
    • Deployment
      On-Demand Dedicated
      Monthly Reserved
    • Parameters
      12B
    • Context length
      64K
    • Input modalities
      Text
      Image
    • Output modalities
      Text
    • Released
      March 1, 2025
    • Last updated
      September 9, 2025
    • External link
    • Category
      Chat