{"id":"tp-42314","type":"article-newspaper","title":"NVIDIA Reports 42.5% Throughput Gain for Ling-3.0-flash-fp4 on DGX Spark","author":"Simon Yoon","publisher":"TOKENPOST Inc.","url":"https://www.tokenpost.com/news/technology/42314","datePublished":"2026-10-28T03:52:28.000Z","dateModified":"2026-10-28T03:52:28.000Z","language":"en","abstract":"NVIDIA's test across all 1,319 GSM8K questions also cut mean latency 24.5%; a synthetic benchmark showed a much larger 185.1% increase.","section":"Technology","references":[{"title":"local AI systems, including DGX Spark","url":"https://www.tokenpost.com/news/technology/37449"}]}