GSM8K
1 article tagged with GSM8K
November 3, 2026
benchmarkNVIDIA
NVIDIA lifts Ling-3.0-flash GSM8K decode throughput 42.5% on a single DGX Spark with 3 MoE optimizations
NVIDIA describes 3 stacked optimizations for Mixture-of-Experts (MoE) inference on a single DGX Spark. On Ant Group inclusionAI's 124B Ling-3.0-flash, GSM8K decode throughput rose 42.5% with no detectable accuracy change.