Micron introduces 24 Gbit GDDR7 memory targeting high end GPUs and Artificial Intelligence PCs

Micron has quietly detailed new 24 Gbit GDDR7 memory chips capable of enabling graphics cards with up to 96 GB of VRAM and targeting next generation gaming and Artificial Intelligence PCs.

Micron has introduced new 24 Gbit GDDR7 graphics memory that is designed to enable graphics cards with as much as 96 GB of VRAM, aimed at next generation gaming systems and Artificial Intelligence PCs. The company chose to present the development in a blog post titled ‘The new performance bottleneck: How more GPU memory unlocks next gen gaming and AI PCs’ rather than through a formal press release, signaling a low key reveal despite the high density capability.

The 24 Gbit GDDR7 chips match offerings already demonstrated by competitors, as Samsung sampled partners with 24 Gbit or 3 GB density GDDR7 memory chips back in November of last year. Samsung’s 3 GB GDDR7 chips are also offering 36 Gbps bandwidth, so Micron does not differentiate on raw bandwidth, with both vendors targeting the same 36 Gbps performance level for their latest parts. Micron instead highlights improved efficiency for its new GDDR7 chips, although it does not provide any specific details on power consumption or architectural changes behind that claim.

Micron’s messaging focuses on the broader benefits of higher density and faster GDDR7 memory for graphics cards and Artificial Intelligence focused PCs, emphasizing how expanded VRAM capacity and bandwidth can alleviate performance bottlenecks in modern workloads. The blog post describes the advantages that GDDR7 at higher density and speeds will bring to gaming, content creation, and Artificial Intelligence driven applications, while omitting concrete specifications beyond density and bandwidth. Despite the announcement, the new GDDR7 chips do not yet appear on Micron’s public product pages, even though the blog post links directly to a GDDR7 product page on the company’s site.

52

Impact Score

Intel holds off on joining Artificial Intelligence RAN Alliance at MWC 2026

Intel is staying out of the Artificial Intelligence RAN Alliance for now, arguing that existing standards bodies and its Xeon CPUs already enable Artificial Intelligence in the radio access network. The stance underscores a broader industry debate over whether future RAN infrastructure really needs GPUs at the cell site.

Contact Us

Got questions? Use the form to contact us.

Contact Form

Clicking next sends a verification code to your email. After verifying, you can enter your message.