GPT-OSS
    GPT-OSS
    Running GPT-OSS on your server with GPU acceleration using ollama.

    Requirements

    8192MB4 vCPU60GB

    Tags

    Deploy time (approx)

    ~10 minutes

    About GPT-OSS

    Run OpenAI’s open-sourced GPT-OSS models (117B / 21B) locally using Docker inside your own codebase. This project avoids third-party GUIs like Open WebUI or LM Studio to help you learn how to use GPT-based models directly in your applications. Use DataCrunch servers 1xA100, 1xA6000 or 1xH100 to deploy this template. Read more about this on our blog: https://docs.dollardeploy.com/blog/openai-gpt-oss/

    About DollarDeploy

    DollarDeploy allows you to easily deploy and manage apps on your own VPS without the need for SSH access. Deploy GPT-OSS with just a few clicks and start building your solution today!