SAN JOSE, CA and TAIPEI, Taiwan, June 4, 2026 – Super Micro Computer introduced rack-scale server systems built around Arm AGI CPUs to handle the rising compute load of agentic AI in enterprise data centers. The systems combine air-cooled and liquid-cooled designs with Arm Neoverse CSS V3-based processors to increase compute density within existing power, space and deployment constraints.
“Supermicro continues to lead the industry when it comes to deploying new and innovative rack-scale solutions that maximize performance and efficiency,” said Charles Liang, president and CEO of Supermicro. “Our DCBBS technology stack delivers end-to-end data center solutions of any size, which combined with the new density and efficient performance optimized Arm AGI CPU microarchitecture, helps enterprises realize significant TCO savings on their agentic AI infrastructure investments.”
“Agentic AI is driving a fundamental shift in infrastructure requirements, where efficiency, scalability, and orchestration performance are becoming just as critical as raw compute,” said Mohamed Awad, executive vice president, cloud AI business unit, Arm. “By combining Arm AGI CPUs with Supermicro’s rack-scale system expertise, we’re enabling infrastructure designed to deliver higher AI throughput, maximum compute density, and improved data center economics at scale.”
The new computing platforms include air-cooled dual-socket 2U compute-optimized servers, 5U GPU-optimized rackmount servers and a liquid-cooled multi-node solution for rack-scale agentic AI deployments. The solutions use its modular server architectures and end-to-end DCBBS capabilities to support rack-scale deployment and reduce time-to-online.
The Arm AGI CPU can deliver more than 2x performance per rack compared with traditional architectures when deployed in Supermicro systems, according to Arm estimates. Arm also estimates that enterprises can save up to $10 billion in CAPEX per gigawatt of AI data center capacity, while Supermicro’s rack density and performance-per-watt improves use of data center space and power resources.
The Arm AGI CPU uses 136-core microarchitecture built for sustained performance, with reduced legacy overhead and more work completed per cycle. Each core supports 6GB/s memory bandwidth, while latency-optimized memory access supports linear scaling. Expanded memory capacity and flexible I/O support thousands of parallel agentic AI tasks, with more than 6,000 cores available in a single air-cooled rack.
The Supermicro Lineup of Arm-Based Servers
2U Hyper Server – Optimized for agentic AI, Cloud, and memory-intensive workloads
- Two Arm AGI CPUs, up to 136 cores per CPU
- Up to 6TB of DDR5-8800 MT/s RDIMMs
- Up to two GPUs
5U GPU Server – GPU-dense configuration for AI training and inference
- Two Arm AGI CPUs, up to 136 cores per CPU
- Up to 6TB of DDR5-8800 MT/s RDIMMs
- Up to 8 double width GPUs
2U4N Liquid-Cooled Server – For OCP ORV3 environment
- Two Arm AGI CPUs per node, up to 136 cores per CPU
- 4 nodes in 2-OU potentially up to 20,672 cores per one ORV3 Rack.
- Up to 6TB of DDR5-8800 MT/s RDIMMs per node
2U Hyper-E Server – Single-socket architecture with front I/O
- Single socket Arm AGI CPU, up to 136 cores
- Up to 3TB of DDR5-8800 MT/s RDIMMs
- Up to 2 GPUs
1U 4N in an OCP ORW rack – Massive Compute Density
- ORW – 48U rack
- 336 Arm AGI CPUs per rack
- 168 servers per rack with 45,696 cores per rack
Source: Super Micro
About Super Micro Computer
Super Micro Computer is a U.S. technology company founded in 1993 and headquartered in San Jose, CA. It designs and manufactures server and storage systems, networking devices and server management software. The company also develops components such as motherboards, power systems and chassis used in its hardware platforms. Supermicro provides products for enterprise data centers, cloud computing, AI, telecommunications and edge computing environments. Its portfolio includes servers, AI systems, storage platforms, IoT systems, switches and related support services. The company designs and manufactures products in facilities in the United States, Taiwan and the Netherlands. Its systems support a range of processors, memory configurations, GPUs, storage and networking options, along with air and liquid cooling methods. Supermicro serves global customers across enterprise and service provider markets. The company employs about 5,000 people worldwide.