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

Observed performance

Run snapshot

All runs matching the filters below.
Fastest run
Median speed
Memory ceiling
Slowest run
Measured runs
Laguna-S-2.1-INT4 — 89.7 tok/s on Multi-GPU · 112 GB ×4 | LocalMaxxing