??Run an AI Model Locally in Your Own Homelab in 5 Minutes - Dell Optiplex 7050
Hardware:
Software:
Step 1: Download and install Ollama Software
curl -fsSL https://ollama.com/install.sh | sh
Step 2: Run Deepseek model with 8B parameters
ollama run deepseek-r1:8b
Step 3: Write a prompt
>>> Hello Linkedin
<think>
</think>
Hello! It seems like you're referring to LinkedIn, the professional networking platform. How can I assist you with LinkedIn? Are you
looking for help with your profile, searching for jobs, or connecting with others? Let me know! ??
Optional steps – Use the Web UI to write prompts.
*Required: Docker + Portainer
Step 1: Create new stack in Portainer
Add this config to Web Editor
version: '3.8'
services:
open-webui:
image: ghcr.io/open-webui/open-webui:main
container_name: open-webui
ports:
- "3000:8080"
volumes:
- open-webui-data:/app/backend/data
environment:
- OLLAMA_API_BASE_URL=https://localhost:11434
restart: unless-stopped
volumes:
open-webui-data:
Step 2: Deploy the stack and RUN
Step 3: Open in web browser https://machine-ip:3000
Step 4: Register
Step 5: FINISH!