DeepSeek V4 Pro is Live → Try it now.

Model Library/Fireworks AI/MiroThinker-1.7
Fireworks Logo Mark

MiroThinker-1.7

Ready
Deploy on Demand
Fine-tune
accounts/fireworks/models/mirothinker-1p7

    Imported from https://huggingface.co/miromind-ai/MiroThinker-1.7

    MiroThinker-1.7 API Features

    Fine-tuning

    Docs

    MiroThinker-1.7 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 MiroThinker-1.7 on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits.

    Metadata

    State
    Ready
    Created on
    5/14/2026
    Kind
    Base model
    Provider
    Fireworks AI
    Hugging Face
    miromind-ai/MiroThinker-1.7

    Specification

    Calibrated
    No
    Mixture-of-Experts
    Yes
    Parameters
    235B

    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