Arista Networks has formally launched its 7060XE7 Series, a new portfolio of 1.6T networking platforms designed to provide the foundation for rack-scale AI infrastructure. The announcement marks a significant strategic shift for the company, moving from standalone high-performance switches to integrated rack-scale systems that address the extreme density, power, and thermal efficiency required by modern AI workloads.

The 7060XE7 Series is built on Broadcom Tomahawk 6 silicon, a cutting-edge chipset that enables 1.6T throughput per switch. Arista is also collaborating with AMD on next-generation compute silicon and NICs to further scale out AI fabrics. The portfolio includes both fixed switch platforms and configurable rack-scale systems, targeting racks for vertical and horizontal AI workflows. All platforms run Arista's Extensible Operating System (EOS), which includes low-latency and intelligent packet buffering to manage the intense microbursts typical of AI communication and collective patterns.

Key Models and Configurations

The 7060XE7 family comprises several models tailored to different cooling and deployment scenarios. The 7060XE7-64PS and 7060XE7-64PRS are 4U rack switches available in Q4, featuring air-cooled systems with support for pluggable Integrated Heat Sink (IHS) and Riding Heat Sink (RHS) optics. IHS is aimed at current air-cooled data centers, while RHS is designed for future liquid-cooled AI fabrics and extreme port density.

The 7060XE7-64PRS-RV3-L is a specialized 2OU liquid-cooled platform for high-density clusters, utilizing 224G SerDes. This system uses DC power from the ORv3 rack and contains no internal fans, integrating directly with liquid-cooled XPU servers to maximize power efficiency. It will be available in Q1 2027.

For environments requiring deployment flexibility and backward compatibility, Arista will offer the 7060XE7-128PE in Q1 2027. This device provides 128 800G ports in an air-cooled 4RU design, using 100G SerDes. All models are designed to support both scale-up and scale-out AI fabrics using air, liquid, and hybrid-cooled technology.

Software and Protocol Innovations

On the software side, EOS serves as the featured network operating system, but the family also supports open-source alternatives such as Software for Open Networking in the Cloud (SONIC) and OpenSwitch. A key highlight of the portfolio is full support for the Open Compute Project's Multipath Reliable Connection (MRC). MRC is an RDMA-based transport protocol that allows a single reliable connection to simultaneously use many network paths over Ethernet.

According to Arista's Kenneth Duda (president and CTO) and Alan Judge (distinguished engineer), MRC enables endstation NICs to stripe traffic across multiple links and paths to the receiver, with out-of-order packets automatically handled. The protocol responds to network congestion signals such as ECN and packet trimming, shifting load to the best-performing paths and avoiding links and paths that cannot reach the destination. In production environments, Arista claims that MRC achieves high fabric utilization with good load balancing while interoperating seamlessly with scale-across and WAN networks using standard dynamic routing protocols.

Beyond MRC, the software also supports advanced load balancing, congestion management, telemetry, diagnostics, and other technologies that are core to AI networking. The combination of hardware and software allows customers to build robust, high-performance AI fabrics that can handle the unique traffic patterns of distributed training and inference.

Industry Context and Competitive Landscape

The 7060XE7 Series enters a rapidly growing ecosystem of vendors targeting the 1.6T Ethernet market. Competitors include Cisco, Nvidia, Celestica, and others, all vying to capture the explosion in AI-driven data center networking demand. Arista's approach emphasizes tight integration between compute, optics, silicon, cooling, and network operating software. The company has already secured strong customer and ecosystem validation from major cloud providers including Microsoft Azure, Oracle Cloud Infrastructure, and Meta, as well as from chip partners AMD and Broadcom.

Sameh Boujelbene, vice president of data center switch and AI networks market research at Dell Oro, highlighted in a LinkedIn post that the 7060XE7 Series is a strong signal of where large-scale AI fabrics are heading: higher bandwidth, better power efficiency, and tighter integration. She noted that Arista's ability to deliver a complete rack-scale solution—not just switches—positions the company well for the next wave of AI infrastructure deployments.

Historically, Arista has been a dominant player in high-speed data center switching, particularly with its 7000 series and the more recent 7800 modular platforms. The 7060XE7 represents a natural evolution, applying the company's expertise in low-latency, programmable networking to the specific requirements of AI workloads. The move to rack-scale systems also reflects broader industry trends, where hyperscalers and large enterprises increasingly demand fully integrated infrastructure stacks to manage power, cooling, and performance at scale.

For organizations planning to deploy AI clusters, the choice between air, liquid, or hybrid cooling is becoming critical. Arista's portfolio offers flexibility: the air-cooled 7060XE7-64PS and 7060XE7-64PRS suits existing data centers, while the liquid-cooled 7060XE7-64PRS-RV3-L is designed for next-generation, denser clusters that require maximum power efficiency. The 7060XE7-128PE provides a middle ground with high port density in a familiar air-cooled form factor.

The timing of the launch is also notable. As AI workloads move from experimental to production, the demand for high-bandwidth, low-latency networking has surged. Ethernet remains the dominant fabric in most data centers, and innovations like MRC help close the gap with proprietary alternatives such as InfiniBand. By embracing open standards and contributing to the Open Compute Project, Arista ensures that its platforms can integrate with a wide range of servers, storage, and software ecosystems.

Looking ahead, the 7060XE7 Series positions Arista to capture a significant share of the AI networking market, which analysts project to grow at a compound annual rate of over 30% through the end of the decade. The company's focus on rack-scale systems, rather than just components, aligns with the purchasing preferences of large cloud providers and enterprises seeking simplified deployment, reduced power consumption, and optimized total cost of ownership.

Source:Network World News