Sign in & create a key
Sign in with GitHub, then create an API key in your dashboard so the CLI and your agents can submit runs.
Loading latest leaderboard stats…
LocalMaxxing
Speed-test your local LLM rig.Compare it with the world.
Community speed tests for local LLM inference. Track speed, compare hardware, and find your optimal setup.
Every number on this site comes from a community-submitted run on real hardware — no vendor speed tests.
Explore the platform
LeaderboardEvery run, ranked. Filter by model, hardware, engine and quantization.ModelsBrowse speed-tested models with real-world speed and eval scores.HardwareGPUs, Apple Silicon and CPU rigs, compared on actual throughput.BenchmarksQuality scores from community benchmarks, run on local setups.MarketplaceBuy and sell hardware with speed-test-backed listings.Get startedFrom bare GPU to a working local AI setup, step by step.
Live from the community
Benchmark scoreboard
Browse all benchmarks →Fresh on the marketplace
Browse marketplace →How it works
Run a speed test
Measure tokens/sec, time-to-first-token and VRAM usage with the CLI, or submit results through the web form.
Climb the leaderboards
Results appear on the public leaderboards immediately — compare models, hardware and engines to find your optimal setup.
