AI · Early access

Ollama hosting on your own server

Run large language models locally with a single command.

Early access. Join the list and we email you when Ollama opens on VPS.

What Ollama does

Ollama packages open large language models such as Llama, Qwen, and Gemma into an easy local runtime with a simple CLI and REST API. Developers use it to run and test models without a cloud API, and it acts as the backend for many self-hosted AI front ends.

Ollama at a glance

License: MIT
Source code: github.com/ollama/ollama
Website: ollama.com
Runs on: Your own server (VPS)
Good to know: Runs on CPU but needs a GPU with enough VRAM for larger models to respond at usable speed.

Local LLM inference for apps
Offline AI development and testing
Backend for chat UIs like Open WebUI

Ollama, connected to the rest of your business

On your domain
Ollama answers at an address like ollama.yourbusiness.com, with SSL and daily backups switched on.
Mail from your address
Ollama sends its emails from your CloudWish business mailbox. Business email
AI with a cap you set
Give Ollama its own AI key with a monthly spend cap. Usage shows as its own line on your bill. AI in your apps (early access)