Built and deployed into production by DALCO.
AMD “Zen 6” architecture, the world’s best server CPU portfolio for the agentic AI era
The AMD EPYC™ 9006 Series spans four purpose-built families, SP7, SP8, 9006X SP7, and 9006 LP, with up to 256 cores and 512 threads of “Zen 6” and “Zen 6c” compute, up to 1.6 TB/s memory bandwidth across 16 channels of 12.8 GT/s MRDIMM, and PCIe® Gen 6 I/O. Purpose-built for the agentic AI era, it runs more agents per watt, per dollar, and per rack while consolidating enterprise workloads. DALCO engineers this into servers sized to the customer.
MAX CORES (EPYC 9996)
WORLD’S HIGHEST THREAD DENSITY
MAX BOOST CLOCK
12.8 GT/s DDR5 MRDIMM
MEMORY BANDWIDTH
I/O CONNECTIVITY
Match the right purpose-built processor to your workload, across agentic AI, cloud, enterprise, and HPC environments.
Designed for highest core density and leadership performance to support AI-first and cloud environments, helping scale agentic workloads, virtual machines, and AI host nodes efficiently.
Deliver balanced compute, memory, and I/O to run business-critical applications, virtualization, and mixed enterprise workloads, alongside emerging agentic AI services.
Accelerate simulation, modeling, and memory-intensive workloads with enhanced cache and bandwidth, enabling faster time-to-insight and supporting agent-driven analysis.
Built for AI host node deployments, enabling efficient, scalable AI infrastructure with optimized performance per system and strong accelerator utilization.
DALCO designs and builds AMD based workstations, servers, and infrastructure solutions tailored to each customer’s specific computing requirements. From HPC and AI to virtualization and cloud, we integrate the latest AMD technologies into systems designed around the workloads they need to perform.
Our long-standing partnership with AMD gives us access to the latest generation of AMD EPYC™ processors and the expertise to select, configure, and integrate the right components for each application. The result is a complete DALCO system built to deliver the performance, efficiency, and reliability your business requires.
Send us the core counts, the memory footprint and the rack constraints you are working with. Our engineers come back with a configuration sized to the job — not a catalogue page.
