AI on Your Gaming PC

What happened

However, a recent crop of projects aims to bring bigger models to much more modest hardware. It won’t run on your old Pentium laptop, but it doesn’t require a supercomputer-like farm of graphics cards, either.

If you want to experiment with LLMs, you typically have a choice of sending your requests to someone else’s computer or fielding a very large GPU (a chip built for many calculations at once, used for graphics and AI) and CPU (the general-purpose processor at the centre of a computer) setup to run models locally. One example is Strata , a project from [Niko1221], which lets you run a 125-billion-parameter LLM (the kind of AI system trained on text to produce text) on hardware you might already have for gaming.

Strata can use several Qwen3.8 model variants , including different quantizations of the original model as well as coding and other specialized versions. Qwen3.8-Flash-Next is a mixture-of-experts model containing 24,576 small experts, of which only ten are needed for each token.