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
Qwen3.6-35B-REAP-Pruned-ratio-0.5-NVFP4 — 133.3 tok/s on NVIDIA GeForce RTX 5070 Ti · 16 GB | LocalMaxxing