--- title: Nvidia's Vera Rubin is shipping, and the numbers are... description: Nvidia has announced that its Vera Rubin platform is in full production and shipping to major customers including OpenAI, CoreWeave, Google Cloud, Microsoft... canonical: https://daily.dev/posts/nvidia-s-vera-rubin-is-shipping-and-the-numbers-are-nvidia-s-own-blzisevob twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Nvidia's Vera Rubin is shipping, and the numbers are Nvidia's own | daily.dev og:description: Nvidia has announced that its Vera Rubin platform is in full production and shipping to major customers including OpenAI, CoreWeave, Google Cloud, Microsoft... og:url: https://daily.dev/posts/nvidia-s-vera-rubin-is-shipping-and-the-numbers-are-nvidia-s-own-blzisevob og:image: https://api.daily.dev/og/posts/bLzISEVob.png og:image:alt: Nvidia's Vera Rubin is shipping, and the numbers are Nvidia's own og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Nvidia's Vera Rubin is shipping, and the numbers are Nvidia's own **[Trends](https://daily.dev/sources/trends)** · 2 min read · 1 upvotes · 0 comments ## Summary Nvidia has announced that its Vera Rubin platform is in full production and shipping to major customers including OpenAI, CoreWeave, Google Cloud, Microsoft Azure, Meta, and Dell. The platform boasts striking specs: 10x token throughput over the previous generation, training large models with one-fourth the GPUs Blackwell required, a custom Vera CPU claimed to be nearly 2x faster than AMD's Turin on Python workloads, and a Spectrum-6 switch hitting 102.4 Tb/s at 95% efficiency at 100,000+ GPU scale. The platform features rack-scale codesign, liquid cooling, NVLink-C2C coherent dual-socket operation, and CXL 3.1 support. However, all performance figures are self-reported by Nvidia and its customers, with no independent benchmarks available. This matters given the scale of the claims. Meanwhile, Nvidia projects ~$393B in revenue for the fiscal year (82% growth), yet its stock has underperformed the broader chip index, suggesting market skepticism around competition, export restrictions, and hyperscaler capex sustainability. ## Content Nvidia's Vera Rubin platform is in full production and shipping to customers. OpenAI, CoreWeave, Google Cloud, Microsoft Azure, Meta, and Dell are all getting racks. OpenAI plans large-scale deployment in Q3. That's the news. The rest is a wall of benchmark claims. And there are a lot of claims. CoreWeave says its NVL72 racks deliver 10x the token output of the previous generation. Nvidia says the Rubin GPU hits 50 petaflops of NVFP4 performance with 22 TB/s of HBM4 bandwidth, 2.8x over Blackwell. The Vera CPU, built around a custom Olympus core, is supposedly nearly twice as fast as AMD's Turin on Python workloads. The NVL72 rack — 72 GPUs behaving as one liquid-cooled unit, no internal cabling — claims 10x more agentic throughput per watt versus Blackwell. Nvidia also says you can run 40% more GPUs within the same power budget using their DSX MaxLPS software. Every one of these numbers comes from Nvidia or its customers. There are no independent benchmarks yet. That's worth sitting with. The figures are impressive on paper, and the architecture details are real — 336 billion transistors, NVLink 6 at 3,600 GB/s, a neural branch predictor in the CPU, Spectrum-6 networking at 102.4 Tb/s. The engineering is clearly serious. But "serious engineering" and "the numbers check out" are different things, and right now we only have one side of that conversation. Nvidia also invested in Ilya Sutskever's Safe Superintelligence, which gets early access to Vera Rubin as part of the deal. Make of that what you will. Meanwhile, Nvidia's stock has underperformed the broader chip index this year despite projecting roughly $393 billion in revenue for the fiscal year — 82% growth. The market, apparently, has already priced in dominance and is now asking what comes after it. The Vera Rubin story is real. The scale is real. The benchmarks need someone other than Nvidia to run them. --- Tags: [#llm](https://daily.dev/tags/llm), [#nvidia](https://daily.dev/tags/nvidia), [#gpu](https://daily.dev/tags/gpu) [View this post on daily.dev](https://daily.dev/posts/nvidia-s-vera-rubin-is-shipping-and-the-numbers-are-nvidia-s-own-blzisevob) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Nvidia's Vera Rubin is shipping, and the numbers are Nvidia's own","url":"https://daily.dev/posts/nvidia-s-vera-rubin-is-shipping-and-the-numbers-are-nvidia-s-own-blzisevob","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/nvidia-s-vera-rubin-is-shipping-and-the-numbers-are-nvidia-s-own-blzisevob"},"datePublished":"2026-07-21T16:39:39.235Z","dateModified":"2026-07-27T14:07:54.108Z","description":"Nvidia has announced that its Vera Rubin platform is in full production and shipping to major customers including OpenAI, CoreWeave, Google Cloud, Microsoft...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/dd2c72dafd2b1ad58c70aa0448dc22e2?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/dd2c72dafd2b1ad58c70aa0448dc22e2?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Trends","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Trends","logo":"https://media.daily.dev/image/upload/s--ZfSp3asX--/f_auto,q_auto/v1780996004/logos/trends?_a=BAMAMiWQ0","url":"https://daily.dev/sources/trends"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/nvidia-s-vera-rubin-is-shipping-and-the-numbers-are-nvidia-s-own-blzisevob","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llm,nvidia,gpu","timeRequired":"PT2M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Trends","item":"https://daily.dev/sources/trends"},{"@type":"ListItem","position":3,"name":"Nvidia's Vera Rubin is shipping, and the numbers are Nvidia's own"}]} ```