DeepSeek V4 Pro is Live → Try it now.

Model Library/Google/Gemma 4 E4B
Google Ai Logo Mark

Gemma 4 E4B

Ready
Deploy on Demand
accounts/fireworks/models/gemma-4-e4b

    Gemma 4 E4B is a pre-trained multimodal base model by Google DeepMind with 8B total / 4.5B effective parameters, a 128K context window, and support for text, image, audio, and video input across 140+ languages.

    Gemma 4 E4B API Features

    On-demand Deployment

    Docs

    On-demand deployments allow you to use Gemma 4 E4B on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits.

    Metadata

    State
    Ready
    Created on
    5/15/2026
    Kind
    Base model
    Provider
    Google
    Hugging Face
    google/gemma-4-E4B

    Specification

    Calibrated
    No
    Mixture-of-Experts
    No
    Parameters
    8B

    Supported Functionality

    Fine-tuning
    Not supported
    Serverless
    Not supported
    Context Length
    131k tokens
    Function Calling
    Not supported
    Embeddings
    Not supported
    Rerankers
    Not supported
    Support image input
    Not supported