alexellis/rigmark

Local-first CLI for benchmarking LLMs on real hardware — quality, speed, reliability, and a real multi-turn agent loop.

Test LLMs on real tasks. Compare models side-by-side.

Benchmark your local LLMs with real evaluation suites. Not vibes - actual scores.

Benchmark your local LLMs: speed, memory, and quality, in one command. TUI leaderboard for Ollama, LM Studio, llama.cpp, and vLLM.

Run the AEON Bench suite on your own hardware: verified HuggingFace pull → serve → benchmark (text · agentic ×3 harnesses · vision · audio · arena · perf) → ed25519-signed attested submit.

discover LLMs punching above their weight

LocalScore is an open benchmark which helps you understand how well your computer can handle local AI tasks.

CLI port of BenchLocal quality bench packs — runs LLM behavioral evals against any OpenAI-compatible endpoint. Companion to club-3090.

Benchmark local LLM serving by replaying real agent trajectories