I’ve been running local AI models for a while now, and the models themselves are only part of the problem. I’ve got different GPUs, a couple of other AI machines, models running in vLLM, and a few ...

I keep most of my AI models on TrueNAS and access them over NFS from several Linux machines. Some of those models are well over 100 GiB, and I don’t really want to maintain a separate copy on every...

I’ve been setting up and rebuilding quite a few machines in my homelab, and one thing I keep doing by hand is installing Ubuntu. Normally, I boot from a USB drive, choose the disk, create an accou...

I’ve been running a few local models, and I don’t really want to choose one before every request. A faster model might handle most of a coding task just fine, but sometimes the agent could run into...

vLLM is an open source inference and serving engine for running AI models on your own hardware. You give it a model and it handles the inference side, and it can also expose that model through an O...

NPUs are showing up in more computers, but their job is still harder to explain than the CPU or GPU. I know what I use a CPU for. I know what I use a GPU for. The NPU was kind of a mystery to me. ...

The easy part of building a mini rack is deciding what goes inside it. You probably already know which switch, mini PC, or storage device you want. Everything after this is the hard part. How do ...

When you buy an NVIDIA DGX Spark or an ASUS Ascent GX10, it ships with DGX OS. DGX OS is NVIDIA’s managed Ubuntu image, and it is fine - if you want a full GNOME desktop on an AI box, but that’s no...

COMPUTEX 2026 was my first hardware show at this scale, and I went in expecting AI to be a major theme. That part was obvious before I even landed in Taipei. What I didn’t expect was how completely...

When I built my local AI cluster on a pair of ASUS Ascent GX10s, the hard part was not serving a model. The hard part was getting a working vLLM image with current components. NVIDIA’s official ima...