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
Qwen3.8-27B-GSQ-3bit-capy-flash — 288.3 tok/s on RTX 5070 Ti · 32 GB ×2 | LocalMaxxing