ResearchBenchmarksConversation on ShareGPTConversation on ShareGPTFollow2.01ThroughputHiSpec1.16761.38631.6051.8237Oct 1, 2025Evaluation resultsMethodMethodLinksThroughputAccuracyHiSpecBase Model=Llama3-8B,...Base Model=Llama3-8B, Accuracy Judge=Llama3.1-70B, Draft Model=None (single model)2025.102.01100SPRINTERBase Model=Llama3-8B,...Base Model=Llama3-8B, Accuracy Judge=Llama3.1-70B, Draft Model=Llama3.2-1B2025.101.240