Samsung laid out a full-stack memory roadmap at this week's Future of Memory and Storage Summit in Santa Clara, spanning HBM4E, HBM5, and two concept architectures—zHBM and zNAND-O—designed to support 10× more AI token throughput by 2030. Leno Park, VP of flash solutions at Samsung Electronics, grounded the roadmap in a concrete problem: AI clusters today support roughly 100 tokens per second per user; Samsung is engineering for 1,000 tokens per second by 2030.

Samsung's AI memory roadmap is engineered to lift cluster token throughput 10× — from ~100 tok/s per user today to 1,000 tok/s by 2030.
FIG. 02 Samsung's AI memory roadmap is engineered to lift cluster token throughput 10× — from ~100 tok/s per user today to 1,000 tok/s by 2030. — Samsung Electronics / Leno Park, Future of Memory and Storage Summit 2026

HBM4E is the nearest deliverable. Samsung shipped samples in May and confirmed active evaluation by major ecosystem partners. The product uses a 4 nm logic base die, increases through-silicon via (TSV) count by approximately 4×, and deploys advanced packaging with more than 300,000 microbumps at tighter pitches. Result: 4 TB/s bandwidth and 64 GB capacity in a single 16-high stack, with I/O speeds of 16 Gbps per pin—more than 20% faster than HBM4. To manage thermal concentration in dense stacks, Samsung added a heat pipe block—a "chimney" placed directly over hot spots.

GenerationBase Die ProcessBandwidthCapacityI/O SpeedKey Technology
HBM4E4 nm4 TB/s64 GB (16-high stack)16 Gbps/pin (>20% faster than HBM4)TSV count ×4; 300K+ microbumps; heat-pipe chimney for hot-spot cooling
HBM52 nm (GAA)Gate-all-around transistors; shortened interposer channels for better I/O signaling
zHBMTBD (co-design)8× HBM5 (claimed)>10× HBM5 density (claimed)Accelerator stacked directly on HBM; 3D unified structure; 3× energy efficiency; <50% thermal resistance vs. HBM5
FIG. 03 Samsung HBM generation roadmap: key specifications and technology milestones — Samsung Electronics, FMS 2026

HBM5 shifts the base die to a 2 nm process using gate-all-around (GAA) transistor technology. Samsung is also shortening interposer channel lengths to improve I/O signaling between base die and accelerator. The node shrink targets another bandwidth-per-watt step before architecture changes with zHBM.

zHBM collapses the 2.5D side-by-side layout of current HBM integration. The AI accelerator sits directly above the HBM stack as a unified 3D structure, cutting physical distance between processor and memory. Samsung claims the next-generation interface could deliver 8× the performance of HBM5, more than 10× memory density, 3× energy efficiency, and less than half the thermal resistance. Reaching those numbers requires close co-design with accelerator partners—limiting adoption to vendors willing to share die-level design data and coordinate packaging.

Integration evolution: today's 2.5D side-by-side HBM layout vs. zHBM's fully 3D stacked structure where the AI accelerator sits directly above the HBM stack.
FIG. 04 Integration evolution: today's 2.5D side-by-side HBM layout vs. zHBM's fully 3D stacked structure where the AI accelerator sits directly above the HBM stack. — Samsung Electronics, FMS 2026

Samsung also announced the V10 BV-NAND, its 10th-generation TLC V-NAND, with 400 layers, an 11% lateral shrink, and 58% higher memory density versus the prior generation. It introduced LPDDR5X-PIM, the first LPDDR memory with processing-in-memory capability, offloading selected data operations into memory to reduce memory-compute round-trips. The PCIe Gen6 PM1763 SSD entered mass production in July 2026 for AI data-center checkpoint and dataset I/O.

ProductTypeKey SpecificationsStatus
V10 BV-NAND10th-gen TLC V-NAND400 layers; 11% lateral shrink; 58% higher memory density vs. prior genAnnounced
LPDDR5X-PIMLPDDR with processing-in-memoryFirst LPDDR-class PIM; offloads data operations into memory to cut memory-compute round-tripsAnnounced
PCIe Gen6 PM1763 SSDData-center NVMe SSDPCIe Gen6; targets AI checkpoint and dataset I/O workloadsMass production — July 2026
FIG. 05 New Samsung storage and memory products announced alongside the HBM roadmap — Samsung Electronics, FMS 2026; StorageReview 2026

Samsung's HBM revenue outlook underscores urgency: HBM sales will more than triple in 2026 versus 2025, and reach 50% of total DRAM revenue by 2030. After 2029, incremental speed bumps won't close the gap. The structural question is whether co-designed 3D integration like zHBM ships on time and at yields that make it usable for procurement decisions, not just roadmap slides. HBM4E at 4 TB/s and 64 GB per stack is available for evaluation now; HBM5 and zHBM remain co-design items—factor that uncertainty into any cluster build beyond 2027.