Version: Latest
OS: Ubuntu 24.04 LTS
Category: AI & Machine Learning
Description
Deploy your own private ChatGPT-like AI assistant in minutes. Complete web interface with access to 50+ open-source AI models, running entirely on your server.
Software Included
Component | Version | License |
Ollama | Latest | MIT |
Open WebUI | Latest | MIT |
Docker | Latest | Apache 2.0 |
Nginx | Latest | BSD-2 |
Key Benefits
Private AI Chat - Your conversations never leave your server
No Usage Fees - Run unlimited AI queries without per-token costs
Ready in 5 Minutes - Complete setup with web interface included
50+ AI Models - Choose from Llama, Mistral, CodeLlama, and more
Getting Started
When you create your VM, installation begins automatically and takes about 1-2 minutes.
Navigate to
http://your-server-ipClick "Get Started" on the main page
Create your admin account
Download an AI model (try
llama2:7bfor general chat)Start chatting with your private AI assistant
System Requirements
Minimum: 4GB RAM, 2 CPU cores, 50GB storage
Recommended: 8GB RAM, 4 CPU cores, 100GB storage
Model sizes: 7B models use ~4GB RAM, 13B models use ~8GB RAM
Common Use Cases
Code assistance and debugging
Content writing and editing
Research and analysis
Learning and education support
Troubleshooting
Can't access interface? Wait up to 2 minutes for installation to complete, then try http://your-server-ip
Models slow to download? Large models (4-40GB) may take 10-30 minutes depending on connection
Need better performance? Upgrade server specs or use smaller 7B models instead of 13B+