Ollama OpenWebUI Raspberry Pi

Install Ollama

curl -fsSL https://ollama.com/install.sh | sh

Install the models

ollama run deepseek-r1:1.5b
ollama stop deepseek-r1:1.5b
ollama run llama3.2:1b
ollama stop llama3.2:1b

Edit Ollama service to point to a ENV file

sudo systemctl edit ollama.service

[Service]
EnviromentFile=/path/to/envs/file

Create /path/to/envs/file

nano /path/to/envs/file

Set env variables

OLLAMA_HOST=0.0.0.0:11434
OLLAMA_MODELS=/path/to/models

If you change the env variables, remember to export them before calling ollama run
Restart services

sudo systemctl daemon-reload
sudo systemctl restart ollama

Set-up Open-WebUI as the UI interface for the AI chat. It is a Docker image.

mkdir ~/OpenWebUI
cd ~/OpenWebUI
nano compose.yml

services:
  open-webui:
    image: ghcr.io/open-webui/open-webui:main
    container_name: open-webui
    volumes:
      - ./data:/app/backend/data
    ports:
      - 3030:8080
    extra_hosts:
      - host.docker.internal:host-gateway
    restart: unless-stopped

docker compose up -d

Using Podman

podman network create open-webui

podman run -d \
-p 3030:8080 \
--gpus all \
-v open-webui:/app/backend/data \
--name open-webui \
--restart always \
--network open-webui \
ghcr.io/open-webui/open-webui:cuda

Allow ports in firewall

sudo ufw allow 11434 # ollama
sudo ufw allow 3030  # open-webui docker

Useful commands

ollama list
ollama ps
ollama show llama3.2:1b

brccabral/01_Readme.md

Ollama OpenWebUI Raspberry Pi