Running LLMs Locally in CPU on our Low End Proxmox Laptop Server
Can you run Large Language Models on an older 8th Gen i3 8130u with reasonable speed?
Ollama Install Script: https://ollama.com/download/linux
Kofi fund - https://ko-fi.com/sjsltech
0:00 Overview
0:34 Proxmox Server
1:00 Creating Debian VM
4:03 Llama3.2 Performance
5:40 DeepseekR1 Performance
7:11 Qwen3 Performance
8:12 Final Thoughts