DeepSeek V4 Pro is Live → Try it now.

Model Library/NVIDIA/Gemma 4 31B IT NVFP4
NVIDIA icon

Gemma 4 31B IT NVFP4

Ready
Deploy on Demand
accounts/fireworks/models/gemma-4-31b-it-nvfp4

    Gemma 4 31B IT NVFP4 - NVIDIA 4-bit quantized variant of Google Gemma 4 31B Instruct for efficient inference

    Gemma 4 31B IT NVFP4 API Features

    On-demand Deployment

    Docs

    On-demand deployments allow you to use Gemma 4 31B IT NVFP4 on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits.

    Metadata

    State
    Ready
    Created on
    4/15/2026
    Kind
    Base model
    Provider
    NVIDIA
    Hugging Face
    nvidia/Gemma-4-31B-IT-NVFP4

    Specification

    Calibrated
    No
    Mixture-of-Experts
    No
    Parameters
    31B

    Supported Functionality

    Fine-tuning
    Not supported
    Serverless
    Not supported
    Context Length
    262k tokens
    Function Calling
    Supported
    Embeddings
    Not supported
    Rerankers
    Not supported
    Support image input
    Supported