SK hynix and Nvidia plan 100M IOPS AI NAND by 2027
SK hynix is pushing hard on next-gen artificial intelligence NAND, and 2027 seems to be its next major milestone, with the company collaborating with Nvidia on ultra-fast artificial intelligence focused NAND chips intended to greatly raise storage performance. According to a ZDNet report, the company is working with Nvidia to build ultra-fast artificial intelligence focused NAND chips that could hit up to 30x the performance of today’s enterprise SSDs. Early samples are planned for late 2026, with second-gen entering mass production by the end of 2027, marking a staged rollout aimed at quickly bringing the new architecture into real-world deployments.
A central pillar of this push is the SK hynix AI-N P high-performance SSD architecture, which is aimed at removing I/O bottlenecks in large artificial intelligence inference workloads where storage throughput can limit accelerator utilization. ZDNet says the redesigned NAND and controller are already in proof-of-concept (PoC) testing with Nvidia, indicating the partners are validating both the media and controller stack together. SK hynix is targeting 25 million IOPS on PCIe Gen 6 for first samples next year, and 100 million IOPS for the production version in 2027. For comparison, current enterprise SSDs manage roughly 2-3 million IOPS (high-end models), which highlights how aggressively SK hynix is trying to exceed existing data center storage performance levels.
The roadmap also includes AI-N B, better known as HBF (High Bandwidth Flash), which is developed with Sandisk to address bandwidth-bound workloads alongside the IOPS-focused AI-N P products. An alpha spec is expected in early 2026 with evaluation units coming in 2027, giving partners time to test and integrate the technology. Behind all these efforts a broader strategy starts to unveil with SK hynix next-gen artificial intelligence NAND chips split into three. First we have AI-N P (ultra-high performance SSD) for performance, AI-N B (High Bandwidth Flash) for bandwidth, and AI-N D (High Capacity/Low Cost SSD) for higher-capacity and lower-cost designs. ZDNet adds that SK hynix views the artificial intelligence market as two distinct fronts: large data-center deployments demanding massive throughput, and on-device artificial intelligence favoring low-power efficiency, with SK hynix positioning its AI-N lineup to serve both with the 2026 AI-N P generation expected to offer roughly 8-10x the performance of current SSDs.