DeepSeek V4 Pro is Live → Try it now.

Model Library/Qwen/Qwen3 Coder 480B Instruct BF16
Quen Logo Mark

Qwen3 Coder 480B Instruct BF16

Ready
Deploy on Demand
Fine-tune
accounts/fireworks/models/qwen3-coder-480b-instruct-bf16

    The BF16 version of the 480B coder model

    Qwen3 Coder 480B Instruct BF16 API Features

    Fine-tuning

    Docs

    Qwen3 Coder 480B Instruct BF16 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 Coder 480B Instruct BF16 on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits.

    Metadata

    State
    Ready
    Created on
    8/13/2025
    Kind
    Base model
    Provider
    Qwen
    Hugging Face
    Qwen/Qwen3-Coder-480B-A35B-Instruct

    Specification

    Calibrated
    No
    Mixture-of-Experts
    Yes
    Parameters
    480B

    Supported Functionality

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