New CLI Tool 'whichllm' Instantly Matches Your Hardware to the Best Local AI Models

May 19, 2026
GitHub
Article image for New CLI Tool 'whichllm' Instantly Matches Your Hardware to the Best Local AI Models

Summary

A new open-source CLI tool called 'whichllm' instantly scans your hardware and recommends the best local AI models you can actually run, ranked by real benchmark data from top leaderboards with a single command.

Key Points

  • A new open-source CLI tool called 'whichllm' auto-detects your GPU, CPU, and RAM to recommend the best local LLMs from HuggingFace that will actually run on your hardware, ranked by real benchmarks rather than model size.
  • Rankings are powered by merged benchmark data from sources like LiveBench, Artificial Analysis, and Chatbot Arena ELO, with recency-aware scoring that discounts stale leaderboards and flags low-confidence or self-reported scores.
  • With a single command, users can simulate any GPU, filter by task profile, instantly download and chat with a recommended model, or generate ready-to-run Python code snippets for seamless local LLM deployment.

Tags

Read Original Article