AI Explained
01 What is Local AI? 02 What is an LLM? 03 Diffusion Models 04 Parameters 05 Quantization 06 Tokens & Context 07 VRAM & Model Size
08 Local Image Generation 09 Local Video Generation 10 LLMs for Everyday Use 11 Multimodal Models
12 The Tools Landscape 13 GeForce RTX for AI 14 DGX Spark & N1X 15 Cloud vs. Local
Calculator Glossary
Foundations
01 — What is Local AI? 02 — What is an LLM? 03 — Diffusion Models 04 — Parameters 05 — Quantization 06 — Tokens & Context 07 — VRAM & Model Size
Use Cases
08 — Image Generation 09 — Video Generation 10 — LLMs for Everyday Use 11 — Multimodal Models
Hardware & Tools
12 — Tools Landscape 13 — GeForce RTX for AI 14 — DGX Spark & N1X 15 — Cloud vs. Local
Tools
VRAM Calculator Glossary
Section 01 — 7 topics

Foundations

The core concepts behind Local AI tool. Here you'll understand exactly why a model says "70B," what quantization does, and what determines whether it fits on your GPU.

01

What is Local AI?

AI used to live in the cloud. Now it can live on your machine — privately, offline, and fast.

02

What is an LLM?

ChatGPT is one. So is Llama. So is Claude. Here's how they actually work.

03

Diffusion Models

How does a computer turn words into a picture? It starts with pure noise and works backwards.

04

Parameters

Why does "70B" matter? Parameters are the knobs the model learned during training.

05

Quantization

Same model, smaller file, almost as smart. How precision trades off against VRAM.

06

Tokens & Context Windows

AI reads in chunks, not letters. Your context window decides how much it can "see" at once.

07

VRAM & Model Size

The single biggest factor in "can I run this?" — with an interactive calculator.

← Back All sections Next section → Use Cases
Home Glossary Calculator

Educational overview. Specs and model availability change frequently. Not an official product guide.