ai models

A practical guide for terminal-first Linux users to run AI locally: recommends top small-to-mid open models (Llama 3, Mistral, Phi-3, Qwen2.5 Coder, Mixtral), shows 5-minute Ollama setup or high-control llama.cpp with GGUF quantization, gives real CLI recipes (explain, summarize, code, logs, commits), tips for speed, context, determinism, and a curl API fallback, keeping data private and costs predictable.

A practical guide for full stack developers and sysadmins to build lightweight, probability-based AI in Bash: why to choose Bash (simplicity, server automation, learning), how to use bc for math, and step-by-step examples including a weighted random decision function and a simple Bayesian inference script—enabling foundational AI directly in shell workflows without heavier tooling.