Pyo
Pyo Cloud
AIby PyoOfficial template

Deploy Ollama on your own servers

Run open models like Llama, Qwen and Gemma behind a local HTTP API.

Get started Ollama website

What Pyo sets up

Image
docker.io/ollama/ollama:0.40.14
Versions
0.40.14, 0.5.4
Reached
Inside the cluster only
Runs as
One replica with its own data
Replicas
1
Requests
1 vCPU · 2 GiB
Limits
4 vCPU · 8 GiB
Storage
30 GiB at /root/.ollama
GPU
1 NVIDIA GPU, used when the cluster has one
Health check
HTTP /

What you can configure

  • Version0.40.14

How to deploy it

  1. 1

    Install Pyo

    Run the setup command on your server.

  2. 2

    Choose Ollama

    Open Templates in the dashboard and pick it. Pyo fills in sensible defaults.

  3. 3

    Deploy

    Pick a server and deploy. Pyo runs it and follows the rollout.

Ports

  • api 11434/HTTPPrivate

Good to know

  • Uses an NVIDIA GPU when its cluster has one, and runs on CPU otherwise.
  • Pull a model with POST /api/pull before the first request. Models are kept on the volume.
  • Models are large: size the volume, memory and GPU memory for the ones you use.

Related templates

All templates

Get Pyo running on your server

Run Pyo on any machine, from your laptop or VPS to a dedicated server or homelab.

curl -fsSL https://pyo.dev/install.sh | bash
View on GitHub