Post

Ollama

Ollama is a tool that allows you to run large language models locally on your own computer. This means you can experiment with and use these AI models without needing an internet connection or relying on cloud-based services. It simplifies the process of managing and running these models, offering a way to keep your data private and potentially work faster. 1 You can use Ollama to create local chatbots, conduct AI research, develop privacy-focused AI applications, and integrate AI into existing systems.

Ollama

Installation

Default install:

1
bash -c "$(wget -qLO - https://github.com/community-scripts/ProxmoxVE/raw/main/ct/ollama.sh)"
CPU: 4 cores RAM: 4096 MB Disk: 40 GB OS: Ubuntu 24.04

Configuration

Config file:

1
/usr/local/lib/ollama

Web Interface

Port: 11434

This post is licensed under CC BY 4.0 by the author.