_____ _ __ _ _ _ _____ _ /__ \ |__ ___/ _(_) (_) ___ ___ _ __ \_ \_ __ __| | _____ __ / /\/ '_ \ / _ \ \| | | |/ __/ _ \| '_ \ / /\/ '_ \ / _` |/ _ \ \/ / / / | | | | __/\ \ | | | (_| (_) | | | /\/ /_ | | | | (_| | __/> < \/ |_| |_|\___\__/_|_|_|\___\___/|_| |_\____/ |_| |_|\__,_|\___/_/\_\

BUYING GUIDES

Best mini PC for a local LLM: /guides/best-mini-pc-for-local-llm/
Strix Halo vs Mac Studio: /guides/strix-halo-vs-mac-studio/
Cheapest hardware for 70B-class models: /guides/cheapest-gpu-for-70b/

HOW GUIDES ARE DETERMINED

prices: official maker list / MSRP only, latest recorded point, linked in SOURCES
fit: weights file size (Hugging Face) + KV cache at 8,192 tokens (model config.json) + 10% overhead, compared with usable memory: VRAM − 1 GB, or 75% of unified / system memory (details)
speed: only published llama.cpp runs; we never estimate tok/s
not_considered: street prices, used hardware, multi-GPU builds, power and noise