Samsung Electronics has finally passed NVIDIA's strict HBM3E 12-Hi memory qualification tests for use on its AI GPUs, with the South Korean memory giant ready to supply 10,000 units.
In a new report from AlphaEconomy picked up by insider @Jukanrosleve on X, NVIDIA recently signed a supply contract for its HBM3E 12-Hi memory to NVIDIA, where the contract will see Samsung supply around 10,000 units of its qualified HBM3 12-Hi product. Samsung commented, saying that everything is "progressing as scheduled".
In previous rumors, Samsung's new HBM3E 12-Hi memory supply was confirmed, but this seems more solid and now a contract is in place, after fellow South Korean memory rival SK hynix has been exclusively supplying NVIDIA with all of the high-end HBM3 and HBM3E memory it needed.
NVIDIA will use the next-gen HBM4 memory standard on its next-gen Rubin AI GPUs and AI servers, with Samsung performing what it hopes to be a huge turnaround in its semiconductor business. We reported just last week that NVIDIA initially requested 9Gbps speeds from HBM4, but pushing for upwards of 11Gbps.
Samsung was the only one to offer HBM4 that could hit 10Gbps+ speeds, with SK hynix needing to pump more voltage (power + heat) to hit those 10Gbps speeds, and US-based Micron said 10Gbps was impossible... so Samsung is looking in great shape for the HBM4 fight in 2026.
