DeepSeek V4 Pro is Live → Try it now.

Model Library/Qwen/Qwen3.5 397B A17B
Quen Logo Mark

Qwen3.5 397B A17B

Ready
Deploy on Demand
Fine-tune
accounts/fireworks/models/qwen3p5-397b-a17b

    The model is served on Fireworks AI in beta mode, constrained generation & tool calls are not yet fully supported.

    Qwen3.5 397B A17B API Features

    Fine-tuning

    Docs

    Qwen3.5 397B A17B 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 Qwen3.5 397B A17B on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits.

    Metadata

    State
    Ready
    Created on
    2/18/2026
    Kind
    Base model
    Provider
    Qwen
    Hugging Face
    Qwen/Qwen3.5-397B-A17B

    Specification

    Calibrated
    Yes
    Mixture-of-Experts
    Yes
    Parameters
    396B

    Supported Functionality

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