t22000t/local-ai-guide

Local AI Guide

A practical guide to running open-weight AI models locally: step-by-step Ollama and llama.cpp setup wired into Claude Code, a hardware analyzer (GPU vs RAM offload, tokens/sec), and a June 2026 model leaderboard with real VRAM requirements.

Source on GitHub: https://github.com/timothy22000/local-ai-guide