DeepSeek V4 Pro is Live → Try it now.

Model Library/Qwen/Qwen 3.5 35B A3B
Quen Logo Mark

Qwen 3.5 35B A3B

Ready
Deploy on Demand
Fine-tune
accounts/fireworks/models/qwen3p5-35b-a3b

    Qwen 3.5 35B A3B MOE model

    Qwen 3.5 35B A3B API Features

    Fine-tuning

    Docs

    Qwen 3.5 35B A3B 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 Qwen 3.5 35B A3B on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits.

    Metadata

    State
    Ready
    Created on
    2/27/2026
    Kind
    Base model
    Provider
    Qwen
    Hugging Face
    Qwen/Qwen3.5-35B-A3B

    Specification

    Calibrated
    No
    Mixture-of-Experts
    Yes
    Parameters
    35.1B

    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