NVIDIA Vera Rubin and Blackwell Set a New Standard for Agentic AI Performance per Watt
<img width="768" height="432" src="https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/image3-4-768x432.jpg" class="webfeedsFeaturedVisual wp-post-image" alt="" style="display: block; margin-bottom: 5px; clear:both;max-width: 100%;" link_thumbnail="" decoding="async" loading="lazy" srcset="https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/image3-4-768x432.jpg 768w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/image3-4-179x101.jpg 179w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/image3-4-300x169.jpg 300w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/image3-4-625x352.jpg 625w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/image3-4-1536x864.jpg 1536w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/image3-4-645x363.jpg 645w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/image3-4-660x370.jpg 660w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/image3-4-500x281.jpg 500w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/image3-4-160x90.jpg 160w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/image3-4-362x204.jpg 362w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/image3-4-196x110.jpg 196w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/image3-4-1024x576.jpg 1024w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/image3-4-960x540.jpg 960w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/image3-4.webp 1920w" sizes="auto, (max-width: 768px) 100vw, 768px" title="image3" />AI agents have expanded inference from single-turn interactions into multi-step workflows that reason, invoke tools, coordinate subagents, and carry growing...<img width="768" height="432" src="https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/image3-4-768x432.jpg" class="webfeedsFeaturedVisual wp-post-image" alt="" style="display: block; margin-bottom: 5px; clear:both;max-width: 100%;" link_thumbnail="" decoding="async" loading="lazy" srcset="https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/image3-4-768x432.jpg 768w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/image3-4-179x101.jpg 179w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/image3-4-300x169.jpg 300w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/image3-4-625x352.jpg 625w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/image3-4-1536x864.jpg 1536w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/image3-4-645x363.jpg 645w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/image3-4-660x370.jpg 660w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/image3-4-500x281.jpg 500w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/image3-4-160x90.jpg 160w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/image3-4-362x204.jpg 362w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/image3-4-196x110.jpg 196w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/image3-4-1024x576.jpg 1024w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/image3-4-960x540.jpg 960w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/08/image3-4.webp 1920w" sizes="auto, (max-width: 768px) 100vw, 768px" title="image3" /><p>AI agents have expanded inference from single-turn interactions into multi-step workflows that reason, invoke tools, coordinate subagents, and carry growing context from one turn to the next. The scale of this shift is now visible in raw consumption: across 100 trillion tokens of real-world usage, OpenRouter’s State of AI report found that average prompt tokens per request grew roughly fourfold…</p>
<p><a href="https://developer.nvidia.com/blog/nvidia-vera-rubin-and-blackwell-set-a-new-standard-for-agentic-ai-performance-per-watt/" rel="nofollow" data-wpel-link="internal" target="_self">Source</a></p>
Read original article ↗
Related Articles
Agentrys Raises $24.5 Million to Build Agentic Design Automation for Chipmakers
Platform from Mark Ren, who pioneered AI for chip design at NVIDIA, enables engineering teams to build and own a self-im
Experiment with Qwen3.8-Flash-Next 176B Model on NVIDIA GB300 NVL72 for Agentic Coding
Alibaba released the model weights for Qwen3.8-Flash-Next as a preview of the upcoming Qwen4 architecture for developers
Top Ten Semiconductor Companies in Q2
NVIDIA USA $125.7 Billion AI GPUs & Data Center Accelerators Samsung Electronics South Korea $72.7 Billion (Memory/DS Di
Restore LLM Inference Capacity in Seconds with Shadow Engine Recovery in NVIDIA Dynamo
When an LLM engine process fails, the standard recovery path involves a cold restart. This requires loading weights into