DeepSeek V4 Pro is Live → Try it now.

Model Library/Qwen/Qwen2-VL 2B Instruct
Quen Logo Mark

Qwen2-VL 2B Instruct

Ready
Deploy on Demand
accounts/fireworks/models/qwen2-vl-2b-instruct

    Qwen2-VL is a multimodal large language model series developed by Qwen team, Alibaba Cloud, available in 2B, 7B, and 72B sizes

    Qwen2-VL 2B Instruct API Features

    On-demand Deployment

    Docs

    On-demand deployments allow you to use Qwen2-VL 2B Instruct on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits.

    Metadata

    State
    Ready
    Created on
    12/2/2024
    Kind
    Base model
    Provider
    Qwen
    Hugging Face
    Qwen/Qwen2-VL-2B-Instruct

    Specification

    Calibrated
    No
    Mixture-of-Experts
    No
    Parameters
    2.44B

    Supported Functionality

    Fine-tuning
    Not supported
    Serverless
    Not supported
    Context Length
    32.7k tokens
    Function Calling
    Not supported
    Embeddings
    Not supported
    Rerankers
    Not supported
    Support image input
    Supported