# NVIDIA Vera Rubin NVL72 on CoreWeave: 10x More Tokens Per Megawatt Than Blackwell

> **Platform:** [SPIDITS AI](https://spidits.com/) — Real-Time AI News & Market Intelligence  
> **Published:** 2026-07-23T14:34:42.000Z  
> **Category:** INFRASTRUCTURE  
> **Impact Score:** 80/100  
> **Primary Source:** [CoreWeave](https://wf.coreweave.com/blog/nvidia-vera-rubin-nvl72-on-coreweave-10x-more-tokens-per-megawatt-than-blackwell)  
> **Canonical Citation:** [https://spidits.com/timeline/nvidia-vera-rubin-nvl72-on-coreweave-10x-more-tokens-per-megawatt-than](https://spidits.com/timeline/nvidia-vera-rubin-nvl72-on-coreweave-10x-more-tokens-per-megawatt-than)

## Executive Summary
CoreWeave publishes first-ever measured silicon performance of NVIDIA Vera Rubin NVL72, marking a new milestone in AI infrastructure.

## Why It Matters (Strategic Analysis)
Crucially, this shifts data center bottlenecks from raw FLOP capacity to memory interconnect bandwidth, setting a new benchmark for agentic workload scaling. As a result, infrastructure providers can support massive reasoning-model throughput within static power boundaries.

## Key Entities & Companies
- **NVIDIA**

## Referenced Coverage & Sources
- **[CoreWeave](https://wf.coreweave.com/blog/nvidia-vera-rubin-nvl72-on-coreweave-10x-more-tokens-per-megawatt-than-blackwell)**: NVIDIA Vera Rubin NVL72 on CoreWeave: 10x More Tokens Per Megawatt Than Blackwell — _CoreWeave publishes first-ever measured silicon performance of NVIDIA Vera Rubin NVL72, marking a new milestone in AI infrastructure._

---
*Synthesized by SPIDITS AI Market Intelligence Desk. Track live AI news, model releases, and funding: [https://spidits.com](https://spidits.com)*