Samsung Leverages NVIDIA Partnership to Become First in the World to Mass-Produce Next-Gen AI Storage Device 'PM1763'
Equipped with NVIDIA's "Vera Rubin"
Twice the Speed of Its Predecessor
Samsung Electronics has become the first in the industry to begin mass production of storage devices for Nvidia's next-generation artificial intelligence (AI) platform. Backed by Nvidia, its largest customer, Samsung aims to solidify its leadership in the AI data center storage device market.
On July 8, Samsung Electronics announced the start of mass production for its new enterprise solid-state drive (SSD), the PM1763. This product will be installed in Nvidia’s next-generation AI platform, Vera Rubin, which is scheduled for release by the end of this year. At the Nvidia annual developer conference, GTC 2026, held in March, Samsung Electronics announced that it would supply HBM4 high-bandwidth memory, SoCAMP2, and the new SSD for Vera Rubin. This means the company is supplying the entire range of memory required for AI servers at once.
An SSD is a storage device that offers much faster read and write speeds than traditional hard disk drives. Enterprise SSDs are designed for data center servers. The new product adopts the PCIe 6.0 standard, which governs the data transfer path between computer components. This standard allows for double the data transfer per cycle compared to the previous 5.0 standard.
The biggest strength is speed. Samsung Electronics has integrated ninth-generation V-NAND and a new controller based on a 4-nanometer process, boosting both performance and power efficiency. For the 16-terabyte (TB) model, the sequential read speed is 28,400 megabytes (MB) per second, and the write speed is 21,900 MB per second—about twice as fast as its predecessor, the PM1753. This enables the transfer of a 40-gigabyte (GB) large language model (LLM) in approximately 1.4 seconds, marking the highest performance in the industry today. The product is available in three capacities: 4TB, 8TB, and 16TB.
Storage speed is a critical factor that determines overall AI server performance. No matter how fast the AI semiconductor is, if the storage device cannot deliver data on time, the costly semiconductor is left idle, waiting for data. As storage devices get faster, AI work efficiency increases accordingly.
Power efficiency has improved by more than 1.8 times compared to the previous generation. In energy-intensive AI data centers, improved power efficiency translates directly into reduced operational costs. The SSD is also designed to accommodate next-generation AI servers that use liquid cooling. By attaching cooling plates directly to semiconductor components, the device can maintain peak performance for extended periods under high-load conditions without performance degradation. Security has also been enhanced, with encryption technology to prevent hacking via quantum computers and technology to secure data transfer paths in virtualization environments.
According to market research firm TrendForce, Samsung Electronics maintained its number one position in the enterprise SSD market in the first quarter of this year with a 35.1% market share. During the same period, sales surged by 92.8% quarter-on-quarter to approximately 7 billion dollars (about 1.06 trillion won), far outpacing overall market growth.
Hot Picks Today
"Two Spend 500,000 Won in a Flash, Yet Wait Two Hours?" ... 'Dreamland' Shunned by Kids and Foreign Tourists
- The Era of Getting 200 Million Won After 30 Years Is Over... A Japanese Bank's "Perpetual Department Head" Who Just Clocked In Cries Out
- Spain Hit by Its Worst Tragedy... Lee Kangin, Moreno and Real Madrid Join Soccer World in Mourning
- They Said, “Make It Your Home for Life” - Then Suddenly Kicked 200 Passengers Off... What Happened to the Around-the-World Cruise?
- "130 Rice Bowls Sold Out in a Day"... 'Unfiltered Face' Adds 8 Million Won to Night Market Sales: China's Bungeunwoo
Jangseok Choi, Senior Vice President of Product Planning Team at Samsung Electronics’ Memory Business Division, stated, "The PM1763, with its industry-leading performance, fully meets the requirements of global clients’ next-generation AI platforms and has successfully completed product validation. By expanding memory capacity, it will serve as a core solution to help clients operate their AI models more efficiently."
© The Asia Business Daily. All rights reserved. Unauthorized AI training and use prohibited.