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

Model Library/Allen Institute for AI/Molmo2-4B

Molmo2-4B

Ready
Deploy on Demand
fireworks/molmo2-4b

    Molmo2 is a family of open vision-language models developed by the Allen Institute for AI (Ai2) that support image, video and multi-image understanding and grounding. Molmo 2 (4B) is Qwen 3-based – optimized for efficiency.

    Molmo2-4B API Features

    On-demand Deployment

    Docs

    On-demand deployments give you dedicated GPUs for Molmo2-4B using Fireworks' reliable, high-performance system with no rate limits.

    Metadata

    State
    Ready
    Created on
    12/29/2025
    Kind
    Base model
    Provider
    Allen Institute for AI
    Hugging Face
    Molmo2-4B

    Specification

    Calibrated
    No
    Mixture-of-Experts
    No
    Parameters
    4B

    Supported Functionality

    Fine-tuning
    Not supported
    Serverless
    Not supported
    Context Length
    36.9k tokens
    Function Calling
    Not supported
    Embeddings
    Not supported
    Rerankers
    Not supported
    Support image input
    Supported