Loading page...Загружаем страницу...正在加载页面...
AtlasRepo

NInfer: 271 tok/s (543 with speculative) for Qwen3.6-35B-A3B on one RTX 5090

**Project Summary:** NInfer is an open-source project that demonstrates impressive performance, achieving 271 tokens per second (543 with speculative execution)

Original source