Huoxing Finance reports that on August 2, analyst qinbafrank clarified market discussions regarding alleged downgrades to NVIDIA’s Rubin HBM, stating that the situation does not involve a downgrade of the standard Vera Rubin NVL72 already in delivery, but rather that the configuration specifications for the upgraded Rubin Ultra, originally planned for release in the second half of 2027, have not yet been finalized. The standard Vera Rubin is progressing smoothly: Dell delivered the first NVL72 systems to CoreWeave in early June and completed the industry’s first full system boot validation; by July, dozens of customers—including Microsoft, OpenAI, Anthropic, Google Cloud, Oracle, Nebius, and SpaceX AI—had received test racks or initial shipments, with some already operational in customer data centers. Large-scale deliveries are set to begin this fall, with overall progress outpacing Blackwell and rack assembly time significantly reduced to approximately five minutes. The aggressive Rubin Ultra configuration announced at GTC 2026—featuring four compute dies approaching mask size limits and 16 HBM4E stacks for ~1TB of memory per package—was questioned by SemiAnalysis and other firms by late June due to challenges with TSMC’s CoWoS-L substrate warping, mask size constraints, and yield issues. The four-die design is reportedly canceled, with NVIDIA likely shifting to a dual-die design matching the standard version, paired with eight HBM4E stacks for ~384GB per package—a substantial reduction from the original target but partially offset by system-level scaling across racks. By late July, TrendForce further noted that Rubin Ultra’s HBM specification remains unconfirmed. Amid supply constraints and rising prices, NVIDIA is prioritizing shipment volume and I/O speed, potentially considering lower-spec options such as eight-layer HBM4E stacks, with the core focus being a balance between capacity and supply certainty. The final specification is expected to be confirmed after validation in the second half of 2026. NVIDIA still targets 2027 for Rubin Ultra shipments, but its overall timeline has shifted from aggressive to pragmatic.
Rumors about NVIDIA Rubin HBM configuration clarified: Standard version delivered, Ultra version still undecided
MarsBitShare
Summary
Rumors regarding NVIDIA’s Rubin HBM configuration were addressed by analyst qinbafrank, confirming that the standard NVL72 version has been shipped to major clients such as Microsoft and Google Cloud. Large-scale deliveries are expected this fall. The Rubin Ultra variant, announced at GTC 2026, remains uncertain due to production challenges. Some firms suggest a design change from four to two chips. TrendForce noted in July that the HBM specifications for Ultra are still unresolved, with NVIDIA prioritizing I/O speed and supply stability. Traders monitoring altcoins to watch may also track the Fear & Greed Index for broader market sentiment shifts.
Source:Show original
Disclaimer: The information on this page may have been obtained from third parties and does not necessarily reflect the views or opinions of KuCoin. This content is provided for general informational purposes only, without any representation or warranty of any kind, nor shall it be construed as financial or investment advice. KuCoin shall not be liable for any errors or omissions, or for any outcomes resulting from the use of this information.
Investments in digital assets can be risky. Please carefully evaluate the risks of a product and your risk tolerance based on your own financial circumstances. For more information, please refer to our Terms of Use and Risk Disclosure.