Build a Local AI Health Dashboard Before Your Lab Gets Weird
Track GPU, disk, containers, and model services in one local AI health dashboard before your home lab becomes guesswork
Home / Tag archive
Archive
GPU guides and notes.
GPU guidance for local AI and ComfyUI builds, covering VRAM, RTX 3090/4090/5090 lanes, starter cards, power, and cooling.
Next route
Turn this topic into a build path.
Tags are useful for discovery. These hubs are better when you need to choose parts, workflows, or a first machine.
Tag archive
Latest in GPU.
7 published posts in this topic.
RTX 5080 for Local AI: When 16GB VRAM Is Enough
A practical RTX 5080 local AI guide: when 16GB VRAM works, when it fails, current price context, and better alternatives
Should You Add a Second GPU to Your Local AI Box?
A practical guide to when a second RTX GPU helps local AI, when it wastes money, and how to split Ollama and ComfyUI workloads cleanly
Windows, WSL, or Linux for an RTX Local AI Box?
A practical guide to choosing Windows, WSL 2, or native Linux for an RTX local AI workstation running Ollama, ComfyUI, and Docker
Stop Downloading the Wrong Local LLM Quant
A practical home-lab guide to choosing Q4, Q5, Q8, and full-precision local LLM files for Mac mini and RTX boxes
Run a Headless ComfyUI GPU Box From a Mac Mini Without Making a Mess
A practical guide to running a headless ComfyUI GPU workstation from a Mac Mini, covering network access, storage, power, security, and buying tradeoffs
Best Starter GPUs for ComfyUI and Local AI: 16GB Cards, Budget Picks, and What to Avoid
A practical starter GPU guide for ComfyUI and local AI builds, covering RTX 5060 Ti 16GB, RTX 4060 Ti 16GB, RX 9060 XT 16GB, and Arc B580