# Self-host Ollama on a VPS, or use an LLM API in India

Source: https://bookmyhost.com/guides/self-host-ollama-llm-vps-vs-api-india (updated 2026-11-20)

A BookMyHost VPS has CPUs only. We do not sell GPU servers. That is enough for small open models in Ollama, but not for large ones. For those, use the AI API.

## The honest limit

On CPU, small models of a few billion parameters run, slowly. Larger models need a GPU, and we do not rent GPU servers. If a model does not fit in RAM, a bigger VPS will not make it fast.


## Option one: the Ollama template

App Hosting has an Ollama and Open WebUI template, CPU only and meant for small models. It starts on the Business plan. It is the quickest way to try a model with a chat screen.


## Option two: Ollama on your own VPS

1. **Create the server** Pick Ubuntu 24.04 with enough RAM for the model you plan to load.
2. **Install Ollama** Run the official installer and pull one small model first.
3. **Keep the API private** Ollama has no login by default. Bind it to localhost or put it behind a firewall and a reverse proxy with authentication.
4. **Measure** Test the speed on your real prompts before you build on it.

## When to use the API instead

Use the AI API for bigger models, or when you need steady speed without managing a server. It is OpenAI-compatible, with the base URL api.bookmyhost.com/v1, so most clients work by changing the URL and key.


## FAQ

- **Do you sell GPU servers?** No. BookMyHost VPS plans are CPU only.
- **Which models fit on a CPU VPS?** Small ones, of a few billion parameters. Test yours before you commit.
- **Is Ollama secure by default?** No. It has no login, so keep it on localhost or behind authentication.
- **Is the AI API compatible with OpenAI clients?** Yes. Change the base URL and key. See AI API.
- **Can n8n call my Ollama?** Yes, over localhost or a private address. See self-hosting n8n.
