NVIDIA Vera Rubin NVL72 delivers 30x more agentic throughput per megawatt
NVIDIA measured up to 30x higher throughput per megawatt than GB300 NVL72 on agentic workloads using the SemiAnalysis AgentX benchmark, with 35x lower token cost. Agentic requests consume 15x more tokens than chat, per OpenRouter data.
How this story unfolded
3 days · 6 reports · 1 community post · 7 of 8 shown
- Aug 22
- Aug 24
SpaceXAI Adopts NVIDIA Vera CPU to Accelerate Agentic AI at Massive Scalenvidianews.nvidia.com
NVIDIA Vera Rubin and Blackwell Set a New Standard for Agentic AI Performance per Wattdeveloper.nvidia.com
Up to 30x More Work Per Watt: NVIDIA Vera Rubin NVL72 Sets a New Efficiency Standard for AI Agentsblogs.nvidia.com
SpaceX ❤️ NVIDIA SpaceX and NVIDIA designed a space-optimized Vera Rubin NVL72 system for an...
- Aug 25
NVIDIA by email
Get an email when NVIDIA has news
No news that day, no email.
More stories today
- ChatGPT users complain it forces local language despite English setting
- New methods steer recurrent reasoners at inference time
- Tencent releases WeMM-Embedding multimodal embedding models
- FireRedTeam releases FireRedAudio and FireRedTTS3
- Mindrank AI CEO discusses AI drug discovery strategy