model management

A Bash-first Linux guide to running private, fast local AI: why go local (privacy, latency, cost, repeatability); how to choose formats (GGUF, safetensors) and runtimes (llama.cpp, Transformers, optional Ollama); steps to install deps, fetch and catalog models with manifests and checksums, run reproducibly, cap CPU/RAM (systemd, nice, cpulimit), host a service, benchmark, quantize, and apply real-world examples.

Hands-on guide to running local LLMs with Ollama on Linux: why it is private, fast, and cost-controlled; step-by-step install for Debian/Ubuntu, Fedora/RHEL, and openSUSE; pull and manage models (e.g., llama3); chat, one-off prompts, and pipe shell data; practical Bash automations; local HTTP API with curl; troubleshooting for PATH, service, and GPU; and next steps to explore more models and integrate into workflows.