Qwen3.8-27BDGX Spark · 4-bit · TensorFoldDecode · tok/s102.9Prefill—tok/100W42.9Qwen3.8-27B just hit 102.9 tok/s on a single DGX Spark with TensorFold.Rank is the quoted 102.9.Officialclaimed@Oluwaphilemon1HFWatchCopy linkOpen pair