What hardware you need to run AI locally: GPUs, Macs and Mac minis, old or CPU-only machines, RAM and storage sizing, and GPU setup tricks. Software setup and model-specific guides stay in Local & Open-Weight Models, and rent-versus-buy cost math goes in Local vs Cloud AI Costs.
Buying a Mac mini to run AI agents all day? Here is how to size RAM and storage, what local models change, and why a bigger machine won't fix agent bloat.
Learn how to run CUDA apps on AMD GPUs with ZLUDA on Windows: setup steps, supported GPUs, legal risk under NVIDIA's EULA, and what still breaks.
Build a local AI coding agent on an M4 Mac Mini with Ollama's MLX backend, Qwen3-Coder-Next, Serena MCP tools, and a Panel chat UI. No token billing.
Quantized GGUF models, BitNet 1-bit weights, and P2P clusters like exo and Petals let you run real AI on a Raspberry Pi or old laptop. Here's the playbook.
Old laptops can run local AI. See how Omarchy Linux and Ollama turn a decade-old, GPU-less machine into a working agentic coding setup.
Learn how developers turn rotary phones, old laptops, Kindles, and spare phones into a subscription-free smart home using open-source local AI scripts.
What GPU, memory, and budget you actually need to run a 27B-class model like Qwen3 locally, plus the break-even math against API pricing.
Local AI vs cloud AI cost, explained with real numbers. Why Apple's M5 Ultra and open models like Granite 4.2 change the local-versus-cloud math.