Latest articles by Richard Devine
Running Ollama on WSL vs. Windows: how does it compare?
AI On Windows 11, you can use Ollama either natively or through WSL, with the latter being potentially important for developers. The good news is, it works well.
A 90-minute podcast from nothing but text — Microsoft’s AI just changed the game
AI Microsoft’s latest AI project is a game-changer for creators
Steam is doing a better job at age verification for its users than Xbox
Gaming Valve's Steam store will be complying (naturally) with the new age verification requirements in the UK Online Safety Act and doing it in a very sensible, less controversial manner.
One of the most powerful mini PCs you've ever seen is a whopping $500 cheaper right now
Deals Mini PCs with an AMD Ryzen AI Max+ 395 APU inside aren't very common right now, and generally really expensive. So how about a huge $500 discount on one?!
Xbox Game Pass — How to choose the right tier for you
XBOX Xbox and PC Game Pass has upended gaming within the Microsoft ecosystem, and here's everything you need to know about getting set up.
What you gain (and lose) with a mini PC like the A9 Max
Review The Geekom A9 Max mini PC is at the pricier end of the spectrum, but when it's an easy replacement for a desktop PC, even for gaming, it makes so much sense.
The best PCs for Photoshop, Illustrator, Premiere Pro, and more
PCs If you're a creator relying on Adobe's suite of products, there are a lot of awesome PCs from which you can choose. These are some of our favorites.
You don't need to spend a fortune on a GPU to run LLMs in Ollama
AI If you're looking at your PC and wondering what sort of GPU you might need to power local LLMs, the good news is it doesn't have to be as expensive as you think. Allow me to explain.
Why an older GPU might crush a newer one for AI
AI If you're running LLMs locally on your PC using Ollama there's one key hardware spec you need to take into consideration. If not, your performance will tank.
Geekom is getting ready to launch a MAD mini PC that'll take it to the Mac Studio
Hardware Geekom's next mini PC, the A9 Mega, is arguably the first true Windows 11-powered competitor to the Mac Studio. Partly because it looks like it, and partly the earth-shattering performance inside.
RECAP: Here's everything Xbox and PC gaming from Gamescom 2025
Gaming Gamescom 2025 brought us exciting news for upcoming video games. Here are all of the biggest Xbox and PC gaming announcements from the show.
The Pact is the next season in The Division 2, coming in September
Gaming Ubisoft has used the first of its Gamescom streams for The Division 2 to outline what's coming next, including the next season, and the one after that.
How to run AI LLMs locally on your PC with Ollama
AI If you want to install and use an AI LLM locally on your PC, one of the easiest ways to do it is with Ollama. Here's how to get up and rolling.
Google's Gemini 2.5 Pro joins Microsoft's GitHub Copilot
AI GitHub Copilot users, at least, the premium ones, will now be able to use Google Gemini 2.5 Pro for all their coding needs. But you can use Google's own tools for free...
I tried to replicate this Copilot feature with local AI, but it's just not the same
AI Using Copilot to summarize web articles is one of my favorite features. I tried to replicate it using an on-device AI model and it just isn't the same.
Why you NEED to use LM Studio over Ollama for local AI if you use AMD or Intel integrated graphics
AI I've been playing with Ollama a lot recently, but it lacks in one key area that has sent me back over to trying LM Studio, with great success, and no need for dedicated GPU.
Intel joins AMD in adding a crucial feature for local AI users
Hardware If you want to leverage even an integrated GPU for AI you need memory, and Intel is following AMD's lead on Core Ultra and allowing you to choose how much you're using.
We gave AI a kid’s exam. It tried its best.
AI 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.
AI on a 7‑year‑old laptop. Because why not.
AI 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.
Even With a Beastly GPU, Ollama Can Lag — Here’s What You’re Missing
AI 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.
Google Is Killing Off Steam for Chromebooks and Dozens Are Upset About It
Gaming Chromebooks were never built to be serious gaming machines, but Google did at least make inroads with Steam. Now, that'll be joining Stadia in the Google Graveyard.
Is OpenAI's new open-source model smarter than a 10-year-old?
AI 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.
Skip the Cloud: 5 Reasons to Use Local AI Instead of ChatGPT or Copilot
AI 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.
