homelab

Pragmatic guide to building a private, low-latency AI GPU homelab on Linux: plan hardware (VRAM, PCIe, power, cooling; NVIDIA/AMD/Intel trade-offs), install drivers/toolkits, set up Docker/Podman with GPU access, and run real workloads (Ollama, llama.cpp, Stable Diffusion, PyTorch). Includes commands, monitoring/optimization (nvidia-smi/rocm-smi, power limits), container tips, troubleshooting, and next steps.

Turn fragile AI homelab tinkering into a repeatable, team‑friendly system with this Bash‑first documentation playbook: auto‑generate hardware/OS inventories, publish a MkDocs Material site, version everything with Git and CI, codify services via Docker/Podman Compose, and back up with restic—complete with cross‑distro commands, experiment templates, restore tests—boosting reproducibility, velocity, and recovery.

Hands-on guide to building a private, reproducible AI homelab on Linux: prep the OS, use Docker/Podman (GPU optional) to run local LLMs with Ollama, add search via Qdrant and a tiny Python RAG script, and transcribe audio with faster-whisper; includes hardware picks, cross-distro install steps, Compose for persistence, updates/monitoring, and troubleshooting—CPU-first, upgradable later.

Hands-on guide to a private, low-latency, all-Linux AI homelab with Ollama: install the daemon, pull/run local LLMs via CLI and HTTP API, optionally accelerate with NVIDIA GPUs, and script Bash automations for logs, man pages, and code; includes copy-paste setup for major distros, secure LAN sharing, maintenance tips, and real-world use cases to cut costs and keep data on‑prem.