AnalysisAI ModelsAugust 12, 2026

124B model runs at 38.7 tok/s on single DGX Spark

A week-long benchmark of a 124B model on one DGX Spark hit 38.7 tok/s on the official INT4 config, 2.4x DeepSeek V4 Flash on the same box. The tester is unaffiliated with the hardware vendor.

1 source

Daily brief

Get tomorrow's AI brief in your inbox

More stories today

Open the live feed