Vue lecture

You Think You Need a Monster PC to Run Local AI, Don’t You? — My Seven-Year-Old Mid-range Laptop Says Otherwise

While most of my local AI work takes place on a fairly well-equipped desktop PC, I was curious to see what mileage I could get from an old laptop I have lying around, and it surprised me.

A Huawei MateBook D running Ollama on Fedora 42

  •  

This Common Mistake in Ollama Could Be Killing Your AI Performance in Windows 11 — Here’s How to Fix It

Ollama is one of the easiest ways to integrate localized AI LLMs into your daily workflow, but you might be leaving performance on the table by making one crucial mistake, like I was.

Ollama stats in Windows Terminal showing eval rate and the split of CPU and GPU being used.

  •  

I Asked OpenAI’s New Open-Source AI Model to Complete a Children’s School Test — Is It Smarter Than a 10-Year-Old?

OpenAI has finally released some AI models folks can use at home on their local machines, so I decided to see if it was better at a test designed for children than my own kid.

Asking the OpenAI gpt-oss:20b model to complete the UK 11+ test designed for 10 and 11 year old children.

  •  

ChatGPT Isn’t the Only Game in Town—Here’s Why Local AI Might Be Better (and How to Use It on Your PC)

AI is far more than the likes of ChatGPT and Copilot, and while these online tools are accessible to all, there are plenty of reasons to start using localized tools on your PC instead.

Ollama running the Gemma3:12b model on a Razer Blade 18.

  •  
❌