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 02 — 4 topics

Use Cases

What you can actually do with Local AI today, on your own hardware. Each topic covers the popular models, the tools that run them, and what kind of GPU you realistically need.

08

Local Image Generation

ComfyUI, Flux, Stable Diffusion — generate images entirely on your GPU.

09

Local Video Generation

HunyuanVideo, Wan 2.x, LTX-Video — video AI is here, and it's heavy on VRAM.

10

LLMs for Everyday Use

Chat, code, summarise your own documents — with Ollama, LM Studio, and Open WebUI.

11

Multimodal Models

Models that read images, hear audio, and output text — and how VRAM math changes.

← Previous section Foundations Next section → Hardware & Tools
Home Glossary Calculator

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