What you run local AI on. For most models the single most important number is memory: a model has to fit before anything else matters. These pages focus on that, plus bandwidth and power, and stay deliberately vague on price, which dates fast.
Enter your GPU or memory and see which models fit, and at what quantisation.
Work out whether buying hardware actually costs less than paying for an API, assumptions included.
NVIDIA · Budget
A budget favourite for getting into local AI. The 12GB variant offers more memory than several pricier cards, which makes it a sensible, affordable entry point for running small and mid-sized models.
NVIDIA · Enthusiast
The high-end consumer GPU that has been the default enthusiast choice for local AI, with 24GB of fast GDDR6X memory and strong compute. Enough to run capable models at good quantisations, though 24GB sets a real ceiling on model size.
Apple · High-end
An Apple Silicon desktop whose unified memory is shared between CPU and GPU, so most of the 64GB is available to models. That makes it capable of running large models that would otherwise need multiple discrete GPUs, at low power.
A quiet, low-power route to running large models at home, built around a Mac Studio with plenty of unified memory. Slower generation than a discrete GPU, but able to hold models that a single consumer card cannot.