Categories › Data & Databases › Files, spreadsheets, CSV & PDFs
Live UK, Germany, Canada and US prices for GPUs and Macs that run open AI models. No sign-up.
Remote server: your requests and data go to readygpu.com. Claude Code: claude mcp add --transport http readygpu-hardware-for-local-ai https://readygpu.com/api/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
search_models — Find open-weight AI models by name or task (chat, coding, agentic, vision, reasoning). Returns each model's slug, size, context length and lfind_hardware — List graphics cards or complete machines (Macs, mini PCs) sold in a market, with memory, bandwidth, the estimated speed on a model and a linhardware_details — One graphics card or machine in a market: its specifications, which models it runs fully in memory at a context length and how fast, and a lhardware_for_model — For one model: how much memory it needs at each context length, and the fastest hardware (and the fastest Mac) that runs it fully in memory best_hardware — The ranked 'best for local AI' lists of a market (all graphics cards, cards under a price, used cards, Macs and mini PCs): best first by thecompare_hardware — Two graphics cards or machines side by side in a market: memory, bandwidth, how many models each runs fully in memory, and the estimated speNot tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.