Fireworks RFT now available! Fine-tune open models that outperform frontier models. Try today

Model Library
/Mistral/Ministral 3 8B Instruct 2512
Mistral Logo Icon

Ministral 3 8B Instruct 2512

Ready
fireworks/ministral-3-8b-instruct-2512

    Mistral's Ministral 3 8B dense model with vision encoder. A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities. This model is the instruct post-trained version, fine-tuned for instruction tasks, making it ideal for chat and instruction based use cases.

    Ministral 3 8B Instruct 2512 API Features

    On-demand Deployment

    Docs

    On-demand deployments give you dedicated GPUs for Ministral 3 8B Instruct 2512 using Fireworks' reliable, high-performance system with no rate limits.

    Metadata

    State
    Ready
    Created on
    12/1/2025
    Kind
    Base model
    Provider
    Mistral
    Hugging Face
    Ministral-3-8B-Instruct-2512

    Specification

    Calibrated
    No
    Mixture-of-Experts
    No
    Parameters
    8B

    Supported Functionality

    Fine-tuning
    Not supported
    Serverless
    Not supported
    Serverless LoRA
    Not supported
    Context Length
    256k tokens
    Function Calling
    Supported
    Embeddings
    Not supported
    Rerankers
    Not supported
    Support image input
    Supported