What is Ollama?
Ollama is a lightweight and efficient server for running large language models (LLMs) on your local machine or in the cloud.
It includes OpenWebUI, a web-based interface for interacting with the models.
Ollama
Run Ollama on Moltern for local LLM hosting supporting Llama, Mistral, Gemma, and custom models with REST API for AI applications.
Service catalog docs