Micron unveils HBMnext, the successor to HBM2e for next-next-gen GPUs

Micron unveils next generation HBMnext memory, which we thought would've been HBM3 -- with a huge 3.2Gbps of bandwidth on tap.

Anthony Garreffa

Gaming Editor

Published Aug 14, 2020 8:26 AM CDT
Updated Nov 3, 2020 11:42 AM CST

1 minute & 15 seconds read time

Micron just finished outing NVIDIA's not-yet-announced GeForce RTX 3090 graphics card, which we now know packs 12GB of ultra-fast GDDR6X memory at 21Gbps.

Micron unveils HBMnext, the successor to HBM2e for next-next-gen GPUs 13

VIEW GALLERY - 2 IMAGES

But they weren't finished with their surprise announcement of the new GDDR6X standard, where Micron has now just announced the development of its next generation memory standard: HBMnext. The new HBMnext memory is most likely what HBM3 was meant to be, but possibly with a new name.

Our friends at VideoCardz report: "Micron expects to produce JEDEC-compliant HBMnext memory in 4-stack 8Gb and 8-stack 16Gb densities. The manufacturer also revealed that the data rate is expected at 3.2 Gb/s. For comparison, the NVIDIA A100 accelerator based on HBM2e technology has a bandwidth of 2.4 Gbps, while AMD Radeon VII based on HBM2 features 2.0 Gbps data rates".

Read more: JEDEC releases HBM4 standard: ready for next-gen AI and HPC memory of the future

HBM2: 2.4Gbps
HBM2e: 2.0Gbps
HBMnext: 3.2Gbps

The company expects to see HBMnext on next-generation graphics cards sometime towards the end of 2022.

News Sources:videocardz.com, media-micron.com, and tweaktown.com

Anthony Garreffa

Gaming Editor

Anthony joined TweakTown in 2010 and has since reviewed 100s of tech products. Anthony is a long time PC enthusiast with a passion of hate for games built around consoles. FPS gaming since the pre-Quake days, where you were insulted if you used a mouse to aim, he has been addicted to gaming and hardware ever since. Working in IT retail for 10 years gave him great experience with custom-built PCs. His addiction to GPU tech is unwavering and has recently taken a keen interest in artificial intelligence (AI) hardware.