AMD EPYC™ 9005 Series Processors

The Choice For Advancing AI and Enterprise Applications

The proven performance, efficiency and easy x86 software compatibility of AMD EPYC™ processors have prompted companies, governments and organizations around the world to switch to EPYC™ processor-based servers for their most demanding computing tasks.

AMD EPYC™ 9005 processors are the newest generation of the powerful and efficient AMD EPYC™ processor family. Designed around the high-performance, high-efficiency “Zen 5” and “Zen 5c”microarchitecture, AMD EPYC™ 9005 processors provide more cores and support for higher frequencies, higher I/O bandwidth, and faster DRAM than the previous generation. High-frequency models excel at optimizing GPU-accelerated systems by efficiently managing data preparation and post-processing tasks.

"Zen 5" Core

This core is optimized for high performance. Up to eight cores are combined to create a core complex (CCX) that includes a 32 MB shared L3 cache. This core complex is fabricated onto a die (CCD), up to 16 of which can be configured into an EPYC™ 9005 processor for up to 128 cores in the SP5 form factor. Compared to the previous generation, 5th Gen AMD EPYC™ processors, powered by the advanced ‘Zen 5’ core, along with faster memory and other key CPU improvements, provide 20% greater integer and 34% higher floating-point performance in 64-core processors operating within the same 360W TDP range.

"Zen 5c" Core

This core is optimized for density and efficiency. It has the same register-transfer logic as the ‘Zen 5’ core, but its physical layout takes less space and is designed to deliver more performance per watt. The ‘Zen 5c’ core complex includes up to 16 cores and a shared 32 MB L3 cache. Up to 12 of these CCDs can be combined with an I/O CCD to deliver CPUs with up to 192 cores in an SP5 form factor.

"Zen 5" CCD with 8 cores per die

"Zen 5c" with 16 cores per die

Leadership Performance, Density, and Efficiency

The AMD EPYC™ 9005 Series uses a hybrid, multi-chip design and new “Zen 5” and “Zen 5c” cores to address data center challenges such as delivering leadership performance, density, and efficiency in virtualized and cloud environments, and supporting new AI workloads. The processor family has a wide range of core counts, including high-frequency products for CPU-based AI inference and fueling GPU-accelerated workloads, high-density CPUs for virtualized workloads, and CXL® 2.0 capabilities for memory-intensive tasks. All processors in the series have support for up to 12 DDR5-6000 memory channels, 128 PCIe® Gen 5 I/O lanes (up to 160 in 2-socket servers), and the AMD Secure Processor to enable virtual machine encryption domains.

EPYC™ 9005 Series At a Glance

AI Leadership

AMD EPYC™ 9005 processors deliver a robust foundation for AI workflows, effectively supporting a wide array of AI workloads on CPU-only server infrastructure, eliminating the need for GPU acceleration. Many AI applications—including large language models, classical image detection, fraud analysis, decision trees, and recommendation systems—run efficiently on traditional CPU architectures. To enhance performance for these workloads, the new 'Zen 5' cores have doubled the data paths. Additionally, these cores include an increased number of integer arithmetic logic units (ALUs), allowing for data processing through a wider pipeline than that of the previous generation processors.

However, some AI workloads require more processing power than a CPU can offer alone. Very large language models, real-time model training, and other demanding generative AI tasks often necessitate advanced GPU solutions. To accommodate this, the AMD EPYC™ 9005 processor family includes optimized models with high core counts and elevated frequencies, specifically designed to serve as host CPUs in GPU-accelerated systems. These processors are engineered to provide the high performance, energy efficiency, memory capacity, and I/O scalability necessary to maximize your investment in GPU technology.

AMD EPYC™ 9005 Processor Specifications