But I would like to hear from you, especially my listeners wanna hear from you about how you're setting up a local AI from the scratch, you know, with the limited budget.

Yep.

So I'll definitely tell you about how I've chosen to do it and, and why.

But before I do that, let me just sort of describe a couple of the key aspects about the hardware and the different categories that we're talking about.

By far, if you're going out there looking to build your own local system and you want to see like the, the narrow set of metrics, by far the most important metric that you could look at i- is VRAM.

VRAM is where your models are gonna be stored.

We're gonna talk about some other more technical terms like KV cache and context and all that sort of stuff.

... models.