Finding the Best Local LLMs for a Normal Home Computer

This content explores running local AI models on a regular home computer, specifically a mini PC with 32 GB of memory. The creator tested six LLMs, ranging from 5B to 35B parameters, including Gemma 4 E2B, Gemma 4 12B, gpt-oss 20B, Gemma 4 26B, Qwen 3.6 35B, and Qwen 3.8 27B. The video details the setup using Ollama over SSH and tmux, measures token generation speed for each model, and concludes with the results and which models were kept.