Run, deploy, and build with local AI models - 16 chapters covering why open-source LLMs matter, the model landscape, model sizes & parameters, running models locally with Ollama, LM Studio & Open WebUI, quantization, hardware requirements, Hugging Face Transformers, vLLM for production serving, building apps with local models, function calling & tool use, multi-modal open models, benchmarks, cost comparison, deployment options, and real-world production case studies.