Archive
Local AI
-

Codex CLI and OpenCode With Ollama: Local Model Setup
Connect Codex CLI or OpenCode to Ollama, choose a local model and check the context setting. Includes remote-server configuration, permission rules and the limits of local-only inference.
-

How to Run Local LLMs on Raspberry Pi 5 with AI HAT+ 2
Assemble Raspberry Pi AI HAT+ 2 on a Pi 5, install hailo-h10-all and hailo-ollama, pull small local LLMs, and optionally add Open WebUI in Docker.
-

Claude Code with Ollama: Run a Local Coding Model
Run Claude Code with a local Ollama model using ollama launch claude. Set a 64k context window, choose a tool-capable model and check the limits before you edit a project.
-

How to Set Up NVIDIA PAIR at Home: Local AI Cluster Guide
NVIDIA PAIR (Personal AI Router) is free beta software that turns the PCs you already own into a small home AI cluster. It does not merge GPUs into one giant card. It routes each local AI request to a machine that can handle it, while keeping prompts on your Wi‑Fi, not in the cloud. If…

