Get startedLeaderboardDecode calculatorModelsReportsHardwareBenchmarksMarketplaceRentalsProAPI 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
Carnice-9b-W8A16-AWQ — 114.3 tok/s on RTX 3090 · 24 GB ×2 | LocalMaxxing