NVIDIA Vera Rubin Records A Massive 30x Increase In Throughput Per Watt Than Blackwell While Offering a 35x Token Cost Reduction Across Agentic AI Workloads – Wccftech

NVIDIA’s Vera Rubin architecture reportedly demonstrates a 30x improvement in throughput per watt compared to its Blackwell predecessor, along with a 35x reduction in token costs for agentic AI workloads, according to Wccftech. The performance gains suggest significant efficiency improvements in power consumption and computational cost for AI inference applications.

Read Full Article →