Get startedLeaderboardDecode calculatorModelsReportsHardwareBenchmarksMarketplaceRentalsProAPI Docs
Language
Actual Computer — Every computer, one endpoint

Observed performance

Run snapshot

Current results after the filters below are applied.
Fastest run
Median speed
Memory ceiling
Slowest run
Measured runs
DeepHermes-3-Mistral-24B-Preview — 24.5 tok/s on RTX 3060 · 12 GB ×2 | Localmaxxing