Overview

Arm Neoverse CSS N4:
Fast, scalable, and flexible

Arm Neoverse CSS N4 is the most configurable Neoverse compute subsystem, with flexible options for CPU cores, cache sizing, memory, and I/O. Silicon designers can target single or multi chiplet systems with Arm's most performant Neoverse N core to date and take advantage of additional time-to-market optimizations over previous CSS generations.

 

Built for next-generation agentic AI data centers, Neoverse CSS N4 delivers rack-scale CPU density, efficient control-plane processing for high-bandwidth network, and high-speed interfacing with AI accelerators. It provides the compute foundation for DPUs that offload security and networking, accelerate AI KV-caching, and isolate agentic AI workloads from the host. Backed by nearly a decade of Neoverse deployments and close partner collaborations, Arm Neoverse CSS N4 provides the fastest path to custom silicon for the agentic AI data center.

Benefits

Built for the demands of AI infrastructure

  • Most configurable Neoverse CSS:

    Configure the number of CPU cores, cache sizing, memory, I/O, accelerator connectivity and chiplet interfaces.

  • Built for agentic AI:

    Power agentic AI infrastructure with up to 2x performance per socket, 1.25x performance per watt and 1.75x memory bandwidth versus the previous generation.

  • Accelerate the path to production silicon:

    Start development earlier and reduce integration effort with a pre-integrated subsystem and early access to development resources.

Neoverse CSS N4 diagram
Inside Neoverse CSS N4

The building blocks of the Neoverse CSS N4 platform

128 cores icon

Configurable from 8 to 128 CPU cores per die

CPU icon

The first N-Series CSS supporting CPU frequencies up to 3.8 GHz

Memory icon

The first Neoverse CSS to support LPDDR6 memory and PCIe Gen 7

Arm Neoverse CSS N4

Visit Arm Product Support for product specifications, technical documentation, downloads, training, security information, and support services.

Talk with an expert

Learn how Arm Neoverse CSS N4 can help you accelerate custom silicon development for agentic data centers.

Contact us
Resources

Latest news and resources

  • NEWS and BLOGS
  • Developer
Generic Guides

Arm advances AI infrastructure momentum

With Arm AGI CPU and Neoverse CSS N4, Arm helps partners build efficient, differentiated AI infrastructure for the agentic AI era.

Read news
Developer icon

Arm Development Studio

Accelerate software development for Arm-based systems with an integrated suite of tools for building, debugging, and optimizing software on Arm-based SoCs.

Explore Arm Development Studio
FAQs

Frequently asked questions

What is the difference between the Neoverse N-Series and V-Series?

The V-Series offers maximum responsive performance with industry-leading Perf/Thread and Perf/Watt at lowest latency. The N-Series offers superior throughput efficiency with industry-leading Perf/Watt and Perf/area.

How can I get started with an Arm Neoverse CSS N4-based design?

Contact an Arm representative here.

What is Arm Neoverse CSS N4?

Arm Neoverse CSS N4 is a configurable compute subsystem that combines Neoverse N4 CPU cores with pre-integrated system IP, software, and reference designs to accelerate cloud and AI infrastructure SoC development. It is supplied as an RTL deliverable that can be imported directly into modern EDA tooling flows. Other deliverables include implementation guidelines, 3rd party IP interoperability support and an integrated software stack that enables users to boot Linux on the compute subsystem for validation or software development.

What can I configure?

Partners can configure core count, cache, memory, I/O, accelerator attach, chiplet connectivity, PCIe, CXL, and other platform options to meet their workload and power targets. To integrate Arm Neoverse CSS N4 into your custom silicon, contact an Arm representative here.

What workloads is Neoverse CSS N4 designed for?

Neoverse CSS N4 is designed for cloud, networking, and AI infrastructure, targeting scale-out compute, web services, cloud native and agentic AI workloads.