Templatesollama
ollama
ai

ollama

Run large language models locally — Llama 3, Mistral, Gemma, Phi, and 100+ models via a simple OpenAI-compatible REST API.

aiutilitiesdevelopment

What gets deployed

Web

ollama server

GitHub stars120,000

About

Run large language models locally — Llama 3, Mistral, Gemma, Phi, and 100+ models via a simple OpenAI-compatible REST API.

Environment Variables

VariableDescriptionRequired
OLLAMA_HOSTDefault: 0.0.0.0Optional
OLLAMA_ORIGINSDefault: *Optional
OLLAMA_KEEP_ALIVEDefault: 5mOptional

Deploy ollama

One click to deploy a fully configured ollama instance with all dependencies pre-wired.

Deploy Now

Ready to deploy ollama?

No infrastructure to manage. Just connect your repo and go live in seconds.