Serverless 2.0 is live: control reliability & speed without reserved capacity. Get Started.

Model Library/Qwen/Qwen3 8B
Quen Logo Mark

Qwen3 8B

Ready
Deploy on Demand
Fine-tune
accounts/fireworks/models/qwen3-8b

    Latest Qwen3 state of the art model, FP8 version 8B Model

    Qwen3 8B API Features

    Fine-tuning

    Docs

    Qwen3 8B can be customized with your data to improve responses. Fireworks uses LoRA to efficiently train and deploy your personalized model

    On-demand Deployment

    Docs

    On-demand deployments allow you to use Qwen3 8B on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits.

    Metadata

    State
    Ready
    Created on
    4/29/2025
    Kind
    Base model
    Provider
    Qwen
    Hugging Face
    Qwen/Qwen3-8B

    Specification

    Calibrated
    Yes
    Mixture-of-Experts
    No
    Parameters
    8.19B

    Supported Functionality

    Fine-tuning
    Supported
    Serverless
    Not supported
    Context Length
    40.9k tokens
    Function Calling
    Supported
    Embeddings
    Not supported
    Rerankers
    Not supported
    Support image input
    Not supported