Having a GPU with 8 GB of VRAM in 2026 doesn’t make you a second-class citizen of local AI. Quite the opposite: LLM models 8GB VRAM have improved so much that you can now run models rivaling paid APIs from…
Having email on your own domain changes how people perceive your brand. It goes from [email protected] to [email protected]. And if you also want end-to-end encryption and genuine privacy, to set up ProtonMail custom domain is one of the best decisions…
You’ve decided to dive into local AI. You’ve read about Ollama, tinkered with interfaces like Onyx or Open WebUI, and now you have a question that keeps you up at night: can my GPU handle this? The short answer is…
You’ve decided to dive into local LLMs and, while looking for an interface, you stumble into the eternal debate: Onyx vs Open WebUI. Great choice, because running an AI model on your own machine, without sending data anywhere and without…
Today I bring you a tutorial I made explaining how to do undervolting and overclocking on your GPU. The results are surprising, and honestly I don’t know why they don’t come like this from the factory. What is undervolting? Undervolting…
