Skip to product information
1 of 1

Arista

Arista DCS-7800R4C-36PE-LC | 7800R4 36-Port 800GbE Line Card, AI-Optimized

SKU:DCS-7800R4C-36PE-LC

Regular price POA
POA
POA
Sale Sold out
Taxes included. Shipping calculated at checkout.

Description

The Arista DCS-7800R4C-36PE-LC is a high-performance 36-port 800GbE OSFP line card designed for the 7800R4 Series modular AI spine switches. Optimized specifically for AI/ML and HPC cluster computing, this R4C variant delivers ultra-low latency, lossless forwarding, and energy-efficient operation. It supports wire-speed breakout to 25G, 50G, 100G, 200G, and 400G, providing exceptional flexibility for large-scale accelerated compute clusters and data center interconnects.

Features

AI-optimized forwarding pipeline for ultra-low latency and high efficiency
- Virtual Output Queuing (VOQ) architecture eliminates head-of-line blocking
- 100% lossless, non-blocking fabric with distributed credit scheduling
- Deep buffering to handle microbursts and incast traffic patterns
- Cell-based fabric spraying for fair distribution across all fabric links
- Wire-speed performance at all port speeds
- Hitless port speed configuration changes
- Support for MPLS and VXLAN overlay protocols
- Accelerated sFlow for advanced telemetry and visibility
- Algorithmic ACL support for efficient policy enforcement
- Compatible with Arista EOS for unified management and automation
- RDMA over Converged Ethernet (RoCE) optimized with DCQCN and PFC
- Ultra Ethernet ready for future AI/ML workloads
- Hot-swappable for continuous operations and serviceability
- Support for copper, AOC, and full range of OSFP optics

Warranty

All products sold by XS Network Tech include a 12-month warranty on both new and used items. Our in-house technical team thoroughly tests used hardware prior to sale to ensure enterprise-grade reliability.

All technical data should be verified on the manufacturer data sheets.

View full details

specs-tabs

Collapsible content

Technical Specifications

FAQs

Technical Specifications

36 x 800GbE OSFP ports
- 800 Gbps per port data rate
- Multi-rate support: wire-speed breakout to 25G, 50G, 100G, 200G, 400G
- 10.8 billion packets per second throughput per line card
- 28.8 Tbps throughput per line card
- Typical power consumption: 25W per port (excludes optics)
- Operating temperature: 0°C to 40°C
- Connector type: OSFP (Octal Small Form-factor Pluggable)
- Compliance: IEEE 802.3bs
- Compatible with Arista 7804, 7808, 7812, and 7816 chassis
- Hot-swappable design
- Front-to-rear airflow
- Routing capacity: up to 256K routes

FAQs

Q: What chassis models is the DCS-7800R4C-36PE-LC compatible with?
A: This line card is compatible with all Arista 7800R4 Series modular chassis including the 7804R4, 7808R4, 7812R4, and 7816LR4 models. It requires compatible R4 fabric modules and supervisor modules to operate.

Q: What makes the R4C line cards different from standard R4 line cards?
A: The R4C line cards are specifically optimized for AI/ML and HPC cluster computing with a simplified, lower latency pipeline and improved energy efficiency. They maintain the same non-blocking, lossless VOQ architecture while delivering better performance for intensive accelerated computing workloads.

Q: Can the 800GbE ports be configured for lower speeds?
A: Yes, each 800GbE port supports wire-speed breakout to multiple lower speeds including 25G, 50G, 100G, 200G, and 400G interfaces. This provides exceptional flexibility for mixed-speed deployments and migration scenarios.

Q: What types of optics are supported on this line card?
A: The line card supports industry-standard OSFP form-factor optics including single-mode and multi-mode fiber transceivers, as well as copper direct-attach cables and active optical cables. For specific transceiver compatibility, consult Arista's transceiver datasheet and EOS release notes.

Q: Is this line card suitable for AI training networks?
A: Yes, the DCS-7800R4C-36PE-LC is purpose-built for AI/ML training networks and HPC clusters. It features an AI-optimized forwarding pipeline, lossless operation with Virtual Output Queuing, and deterministic performance under 100% load conditions—critical for minimizing job completion times in large-scale AI workloads.

Recently Viewed

  • Request a Quote

    Looking for competitive pricing? Submit a request, and our team will provide a tailored quote that fits your needs.

  • Contact Us Directly

    Have a question or need immediate assistance? Call us for expert advice and real-time support.

    Call us Now  
  • Contact Us Directly

    Have a question or need immediate assistance? Call us for expert advice and real-time support.

    Contact us