Samsung Shows Off 32Gb/s GDDR7 Memory Modules at Nvidia GTC

Nvidia's GTC conference this week was all about AI and included the announcement of its next-generation Blackwell architecture. The data center hardware unveiled at the show uses high-bandwidth memory (HBM), so it's not too surprising to hear Samsung was at the event as well since it makes that kind of memory. However, it is now being reported that the company was also showing off its upcoming GDDR7 modules for gaming GPUs. The trade show sighting gives us the first concrete info on the speeds that may be offered when the new memory arrives in GPUs this year.

German website Hardwareluxx was at the show wandering around and spotted a previously unnoticed display at the Samsung booth touting the benefits of its GDDR7 memory solution. What makes this interesting is there's been some confusion about the specs of the first GDDR7 modules that will come to market, as we've heard about a range of offerings spanning 28Gb/s up to 36Gb/s. The placard at the Samsung booth states it's offering 2GB modules running at 32Gb/s, which could be what we see coming to future GPUs from both Nvidia and AMD. However, Hardwareluxx reports that even though 32Gb/s modules were on display, Nvidia will opt for 28Gb/s chips for the RTX 50 series to assist with efficiency.

Even though Samsung was flashing these chips at the show, it's unclear if Nvidia will be using its modules for the RTX 50-series GPUs. Credit: Hardwareluxx.de

The site states that 28Gb/s modules will still mark a 17% improvement in bandwidth compared with the existing GDDR6X modules used on high-end Nvidia GPUs and that 32Gb/s chips would eventually boost that number to 33%. Along with offering more bandwidth, these new modules will also be quite efficient. Samsung notes its GDDR7 modules can run at 1.1V instead of the 1.35V required by GDDR6X memory. Additionally, Samsung says its "optimized circuit design" allows for a 70% reduction in thermal resistance, so they should be easier to cool than GDDR6/X chips AMD and Nvidia currently use.

We'll have to wait and see where the chips fall when both AMD and Nvidia announce their next-generation GPUs, as it's still unclear if Nvidia will be using Samsung modules in the RTX 50 series. In the past, Nvidia exclusively used Micron's GDDR6X chips for its high-end cards, and Micron has announced it'll come to market with 32Gb/s modules later this year. JECEC has already published the specifications for GDDR7, so we know it'll arrive this year; it's just unclear who will use which companies' modules and at what speeds. Now that Samsung has given us a glimpse at what it's offering, Micron and SK Hynix will hopefully release more info soon.