DeepSeek V4 Pro is Live → Try it now.

Model Library/Qwen/Qwen3 Omni 30B A3B Instruct
Quen Logo Mark

Qwen3 Omni 30B A3B Instruct

Ready
Deploy on Demand
accounts/fireworks/models/qwen3-omni-30b-a3b-instruct

    Qwen3-Omni is a natively end-to-end multilingual omni-modal foundation model. It processes text, images, audio, and video.

    Qwen3 Omni 30B A3B Instruct API Features

    On-demand Deployment

    Docs

    On-demand deployments allow you to use Qwen3 Omni 30B A3B Instruct on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits.

    Metadata

    State
    Ready
    Created on
    12/19/2025
    Kind
    Base model
    Provider
    Qwen
    Hugging Face
    Qwen/Qwen3-Omni-30B-A3B-Instruct

    Specification

    Calibrated
    No
    Mixture-of-Experts
    Yes
    Parameters
    35B

    Supported Functionality

    Fine-tuning
    Not supported
    Serverless
    Not supported
    Context Length
    65.5k tokens
    Function Calling
    Supported
    Embeddings
    Not supported
    Rerankers
    Not supported
    Support image input
    Supported