Micron Technology Begins Mass Production of HBM4 Memory for NVIDIA

robot
Abstract generation in progress

Micron Technology announced on March 16th local time that its HBM4 production line has begun mass production and shipment in the first quarter of this year. The first batch of products is a 36GB, 12-layer stacked (12-high) version, designed specifically for the Vera Rubin platform. The company stated that compared to the previous generation HBM3E, HBM4 offers approximately 2.3 times the performance, with more than a 20% improvement in power efficiency. Additionally, Micron has provided early samples of a 48GB HBM4 with 16-layer stacking (16-high) to customers. Compared to the 12-layer version, this model has a 33% increase in single-chip capacity, further enhancing the available memory capacity per HBM module. (Jiemian News)

View Original
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • Comment
  • Repost
  • Share
Comment
Add a comment
Add a comment
No comments
  • Pin