Arista Networks has taken the wraps off its 7060XE7 Series, a new portfolio of 1.6T networking platforms designed to provide the foundation for rack-scale AI infrastructure. The 7060XE7 family features fixed switch platforms and configurable rack-scale systems, targeting racks for vertical and horizontal AI workflows. All will 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, Arista stated.
Platform Overview
The 7060XE7 family is built on Broadcom Tomahawk 6 silicon. Tomahawk 6 is the latest generation of high-capacity switch ASICs from Broadcom, offering up to 1.6 Tbps of bandwidth per chip. This enables the 7060XE7 switches to handle the extreme density and performance requirements of modern AI workloads. Arista is also working with AMD on next-generation compute silicon and NICs to enable scale-out AI fabrics, the company said.
Strategically, the 7060XE7 Series signifies Arista’s transition from offering standalone, high-performance switches to providing rack-scale systems that can handle the extreme density, power, and thermal efficiency AI requires. The platforms allow customers to build scale-up and scale-out AI fabrics using air, liquid and hybrid-cooled technology. This flexibility is critical as data centers grapple with the growing heat output of AI accelerators.
Specific Configurations
The portfolio includes several specific configurations tailored to different deployment scenarios. The 7060XE7-64PS and 7060XE7-64PRS are 4U rack switches available in Q4 2026. These air-cooled systems support 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, featuring 224G SerDes. This system uses DC power from the ORv3 rack and contains no internal fans, integrating with liquid-cooled XPU servers to maximize power efficiency. It will be available in Q1 2027. Additionally, the 7060XE7-128PE provides 128 800G ports in an air-cooled 4RU design, utilizing 100G SerDes, for environments requiring deployment flexibility and backward compatibility. This model also arrives in Q1 2027.
Software and Open Standards
On the software side, EOS is the featured network operating system, but the family also supports open-source software such as Software for Open Networking in the Cloud (SONIC) and OpenSwitch. This dual support allows customers to choose between Arista’s proprietary features and open standards, depending on their operational needs.
One of the portfolio’s key features is the full support for 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 and Alan Judge, “MRC is an open protocol where endstation NICs stripe their traffic across multiple links and paths to the receiver, with out of order packets automatically handled.” MRC responds to network congestion signals such as ECN and packet trimming, shifting load to the best-performing paths, and avoiding links and paths that can’t actually reach the destination. The protocol monitors each path, steering around congestion, avoiding paths with link errors, and avoiding failed links. This approach achieves very high fabric utilization with good load balancing, while interoperating seamlessly with scale-across and WAN networks utilizing standard dynamic routing protocols.
The software also supports advanced load balancing, congestion management, telemetry and diagnostics, and other technologies that are core to AI networking, Arista stated.
Industry Context and Ecosystem
The new Arista family joins a growing ecosystem of vendors looking to tap into the 1.6T Ethernet world, which includes Cisco, Nvidia, Celestica and others. This competition underscores the rapid evolution of AI networking, where bandwidth and latency are paramount. Arista’s focus on rack-scale systems reflects a broader industry shift toward integrated, high-efficiency designs that can support the massive parallelism required by large language models and other AI workloads.
Sameh Boujelbene, vice president of data center switch and AI networks market research for Dell Oro, highlighted the significance of the announcement. Among the features that stand out are strong customer and ecosystem validation from Microsoft Azure, Oracle Cloud Infrastructure, Meta, AMD, and Broadcom. This level of endorsement indicates that Arista’s new switches are not just theoretical designs but are being shaped by real-world requirements from some of the largest AI operators.
The 7060XE7 Series builds on Arista’s established track record in data center networking. For over a decade, the company has been a key player in high-speed Ethernet switching, particularly with its 7000 series. The new generation leverages lessons from previous designs while addressing the unique demands of AI infrastructure, such as handling microbursts and providing deterministic low latency. Arista’s EOS has been a differentiator in the market, offering programmability and consistency across the product line.
Looking ahead, the 7060XE7 family is poised to become a central component in AI data centers. The combination of Tomahawk 6’s bandwidth, MRC’s multipathing, and Arista’s operational software creates a compelling solution for both scale-up and scale-out architectures. With availability beginning in Q4 2026 and expanding in Q1 2027, customers have a clear roadmap for upgrading their AI networks to 1.6T speeds. The platform’s support for multiple cooling options also future-proofs deployments as data center thermal management evolves.
Source: Network World News