Ollama

Deploy Ollama on Out Plane to run large language models on your own infrastructure with full data privacy. Ollama supports Llama 3, Mistral, Gemma, Code Llama, Phi, Qwen, and dozens of other open-source models. Pull any model from the Ollama library with a single command and serve it through an OpenAI-compatible REST API.

Ollama handles model quantization, GPU memory management, and concurrent request handling automatically. The API is compatible with the OpenAI chat completions format, making it a drop-in replacement for OpenAI in any application that uses the standard API. Self-hosting on Out Plane keeps your prompts, completions, and fine-tuned models private.

Ideal for AI application development, private LLM inference, code generation, RAG pipelines, chatbots, and any use case where you need local LLM inference without sending data to third-party AI providers.