Models & Labs

NVIDIA Vera Rubin NVL72 Boosts AI Agent Efficiency

NVIDIA BlogAugust 24, 2026high confidence

Why it matters

→NVIDIA's Vera Rubin NVL72 dramatically increases efficiency for AI agent workloads, crucial for scaling AI applications.
→The system's design reduces the cost per million tokens, making AI deployments more economically feasible.
→This advancement positions NVIDIA as a leader in AI infrastructure, particularly for power-constrained environments.

NVIDIA Vera Rubin NVL72 Boosts AI Agent Efficiency — ©NVIDIA Blog

NVIDIA has unveiled the Vera Rubin NVL72, a system that significantly enhances the efficiency of AI agent workloads. It achieves up to 30 times higher throughput per megawatt than the previous GB300 NVL72 model. This improvement is vital for agentic AI tasks, which require extensive computational resources due to their complex nature. The system's design includes advanced features like disaggregated serving and large-scale expert parallelism, which contribute to its superior performance. This development underscores NVIDIA's commitment to advancing AI infrastructure, particularly in power-constrained settings.

Read original

The story around this

Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.

NVIDIA Vera Rubin NVL72 Boosts AI Agent Efficiency

3 developments

Aug 24 · NVIDIA Blog
NVIDIA Vera Rubin NVL72 Boosts AI Agent Efficiency (This article)
Aug 24 · NVIDIA Blog
NVIDIA Extends Vera Rubin for Agentic AI Inference
Aug 29 · TechCrunch AI
Nvidia Expands AI Advantage Beyond GPUs↳ Nvidia shifts focus from GPUs to orchestrating AI systems and optimizing megascale data center infrastructure with Vera Rubin.

More in Models & Labs

Models & Labsmodels

llama.cpp b12029 adds CUDA 13 and Snapdragon support

This release quietly cements llama.cpp as the universal inference runtime by finally supporting NVIDIA's latest CUDA 13 stack alongside AMD's ROCm 10.0. The inclusion of native builds for Linux arm64 with Snapdragon chips, covering CPU, Adreno GPU, and Hexagon NPU, signals a serious push into mobile edge deployment. While Apple Silicon KleidiAI is disabled in this specific build, the broader hardware coverage means developers no longer need to compile from source for most modern accelerators. It’s less about new features and more about removing friction for anyone running local models on bleeding-edge or diverse hardware.

llama.cpp ReleasesNov 1, 2026

Models & Labsother

Apple Intelligence arrives in China via iOS 27.3

Apple is finally unlocking its AI suite for Chinese users with the iOS 27.3 beta, marking a significant regulatory milestone after months of approval delays. The rollout relies on Alibaba’s Qwen model rather than OpenAI, integrating features like notification summaries and visual intelligence directly into the OS. By sidestepping the new Siri in favor of established text and image tools, Apple is prioritizing immediate utility over the full generative experience. This move effectively brings Apple’s AI capabilities to a massive new market, albeit with localized constraints that distinguish it from the global release.

The Verge AIOct 30, 2026