ResearchTasksLarge Language Model Inference PerformanceLarge Language Model Inference PerformanceFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedIntel Ice Lake / AMD Zen4 AVX-512 VNNILitespark-Inference556Memory (MB)4Jun 11, 2026