optional · 33 ready setups
Start from a ready GPU template.
The GPU boots with the template already installed. The AI builds on it according to your description.
Run your own AI model: a chatbot, assistant or API for apps and bots.
Llama.cpp
AI models & chat
Run your own model as a chatbot, assistant or API.
Run your own AI model: a chatbot, assistant or API for apps and bots.
Use this template →vLLM
AI models & chat
High-throughput inference engine with an OpenAI-compatible API.
Run your own AI model: a chatbot, assistant or API for apps and bots.
Use this template →vLLM Omni
AI models & chat
vLLM with multimodal models.
Run your own AI model: a chatbot, assistant or API for apps and bots.
Use this template →Oobabooga Text Gen UI & API
AI models & chat
Text generation UI and API.
Run your own AI model: a chatbot, assistant or API for apps and bots.
Use this template →SGLang
AI models & chat
Fast structured inference.
Run your own AI model: a chatbot, assistant or API for apps and bots.
Use this template →Ollama
AI models & chat
Pull and run open models with one command.
Run your own AI model: a chatbot, assistant or API for apps and bots.
Use this template →Open WebUI (Ollama)
AI models & chat
ChatGPT-style UI on top of Ollama.
Run your own AI model: a chatbot, assistant or API for apps and bots.
Use this template →HuggingFace TGI API
AI models & chat
Text Generation Inference server.
Run your own AI model: a chatbot, assistant or API for apps and bots.
Use this template →Langflow (Ollama)
AI models & chat
Visual agent builder with Ollama models.
Run your own AI model: a chatbot, assistant or API for apps and bots.
Use this template →Select a template above, or launch without one.Skip, describe from scratch →