Show HN: Find the best local LLM for your hardware, ranked by benchmarks

**whichllm** is a tool that automatically detects your hardware (GPU/CPU/RAM) and recommends the best-performing local language models from HuggingFace that will actually run on your system, ranked by real benchmarks rather than just model size. It provides multiple installation options and customizable commands to simulate different hardware configurations, adjust performance thresholds, and compare upgrade paths before purchasing new equipment. The tool prioritizes evidence-based rankings from merged benchmarks like LiveBench and Chatbot Arena over simple size-fitting heuristics.