Browsing: local AI

A practical guide to running AI models offline on an Android phone or iPhone: the apps that do it, which small models to download, how much memory you need, step-by-step setup and what still needs a computer, including video generation.

A complete reference for the Ollama command line: model management, chat and run flags, in-chat slash commands, server settings and environment variables, Modelfile basics, the local REST API and fixes for common problems.

Which video editors run their AI features on your own computer rather than in the cloud: DaVinci Resolve Studio, Final Cut Pro, Kdenlive and Topaz Video compared on features, price and privacy, plus a simple test to check any editor yourself.

A buyer’s guide to hardware for running large language models at home: how much memory each model size needs, why bandwidth decides speed, and how NVIDIA graphics cards, Apple silicon Macs, AMD Ryzen AI Max mini PCs and NVIDIA DGX Spark compare.

A practical walkthrough for generating AI video on your own computer: what hardware you need, how to install ComfyUI, which model files go where, how to run text-to-video and image-to-video, and how to fix out-of-memory errors.

Which open video models run on your graphics card: VRAM and system RAM requirements for Wan 2.2, LTX, HunyuanVideo 1.5 and CogVideoX, taken from each official repository, with a free checker that matches models to your GPU.

A complete guide to local AI: why people run models on their own machines, what hardware and software you need, which models fit which job, how it compares with paying for an API, and links to every detailed guide in our series.

How to run AI models offline in 2026: the download-once setup with Ollama or LM Studio, quantized models, air-gapped deployment and the hardware you need.