Samsung to Start HBM4 Production for Nvidia's Vera Rubin Platform
Samsung Electronics is preparing to start mass production of HBM4 in the third week of the month. The memory is intended for Nvidia's new Vera Rubin AI platform and has already passed Nvidia's certification. Nvidia is expected to unveil products with HBM4 at the GTC conference next month.
AI-processed from 36Kr (36氪); edited by Hamidun News
Samsung Electronics is preparing for an important step in high-performance memory: the company plans to begin mass production of HBM4 in the third week of this month. The move matters because Nvidia will be the first major customer for the new memory, planning to use HBM4 in its new AI computing platform, codenamed Vera Rubin.
The decision to start mass production came after HBM4 successfully passed Nvidia's certification tests. That is a key factor, since meeting Nvidia's standards is critical for integrating memory into leading AI platforms. Given Nvidia's plans for Vera Rubin, Samsung adjusted its production schedule to ensure timely delivery of the required volume of memory.
HBM4 is the next generation of high-performance memory, designed to meet the growing speed and bandwidth demands of modern AI applications and high-performance computing. Compared with previous generations, HBM4 offers significantly improved bandwidth and energy efficiency, which makes it an ideal fit for data-intensive workloads.
Nvidia is expected to present the Vera Rubin platform, equipped with Samsung's HBM4, at its annual developer conference GTC (GPU Technology Conference) next month. GTC is one of the industry's key events, where Nvidia showcases its latest developments and technological advances. The announcement of Vera Rubin with HBM4 will undoubtedly be one of the most anticipated events of the conference.
The adoption of HBM4 will have a substantial impact on the AI and high-performance computing industries. Greater bandwidth will allow more powerful and efficient systems for training neural networks, analyzing big data and other resource-intensive tasks. This, in turn, will speed up progress in fields ranging from autonomous vehicles to medical research.
For Samsung, the start of HBM4 production is an important step in strengthening its position in the high-performance memory market. The company is investing actively in developing and manufacturing advanced technologies to meet growing memory demand from the AI industry and other sectors. Its successful collaboration with Nvidia on Vera Rubin confirms Samsung's technological leadership and its ability to develop solutions that meet the most demanding requirements.
Thus, the launch of Samsung's HBM4 production opens a new era for high-performance memory, creating opportunities for more powerful and efficient AI systems. The technology is expected to become a key factor in the further development of artificial intelligence and high-performance computing.
- Nov 2, 2026TensorFold 1.2.0 boosts Qwen3.8-27B throughput on M3 Ultra by 44.2% at 16 streams
- Nov 1, 2026Local models lose to Opus and Codex: 0.21 on a MacBook versus 1.00 for Codex
- Nov 1, 2026Habr author fine-tunes YOLOv8l on dental X-rays and pushes mAP50 to 0.642
- Nov 1, 2026Voice bots built on LLMs turn to Jev, a fast classifier, for decisions in 200–500 ms
Test Frontier LLMs & Autonomous Agents in One Workspace
Run Claude Opus 5.5, GPT-6, Gemini 3.1, and DeepSeek side-by-side in Nomad AI (nomadnet.ai) — unified model routing, deep research, and multimodal workflows under one subscription.
The AI world, distilled — once a week
Seven stories that actually mattered, hand-picked. No noise, no reposts, no press releases.
Done! Check your inbox for a confirmation.