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
TinyLlama-1.1B-Chat-v0.3-GGUF — 1,854.7 tok/s on RX 9070 XT · 16 GB | LocalMaxxing