Skip to product information
1 of 1

Cisco

Cisco UCSC-885A-M8-H11 | UCS C885A M8 8-GPU H100 Rack Server, 8x 400GbE, 2.3TB

SKU:UCSC-885A-M8-H11

Request Quote
Sale Sold out
Shipping calculated at checkout.

Stock Status: Enquire

 Trade supply only. Server & GPU quote requests need a company name, ABN and work email address. We do not quote Gmail, Outlook or Hotmail addresses, or supply for home use. 

20-min response

Need a quote or bulk pricing? Answered within 20 minutes, Sydney business hours.

Custom Built Servers

Need a different spec, quantity or configuration?

We build configured-to-order refurbished servers from Cisco, Dell, HPE, NVIDIA Lenovo and Supermicro. Tell us what you need and we'll come back with options within 24 hours.

Configure your server now →

Description

The UCS C885A M8 is an 8RU, fixed-configuration rack server from the Cisco UCS C-Series, built for AI and machine learning model training, large-scale GPU compute and HPC. It is designed as a building block for enterprise AI POD deployments aligned with NVIDIA's Enterprise Reference Architecture.

This H11 configuration pairs eight NVIDIA HGX H100 SXM GPUs with two AMD EPYC 9554 CPUs and 24 x 96GB DDR5 5600 DIMMs, giving 2.3TB of system memory. Networking is handled by eight NVIDIA ConnectX-7 1x400GbE adapters for east-west GPU scale-out and one BlueField-3 B3220 NIC for north-south storage and front-end traffic. Local storage is 16 x 1.92TB NVMe SSDs, with an OCP 3.0 Intel X710 T2L 2x10GbE NIC for LAN connectivity.

Power comes from six 3000W 54V AC supplies in a 4+2 arrangement plus two 2700W 12V Titanium supplies, with maximum system power of approximately 12.5 kW. It is designed to work with Cisco Nexus 9364E-SG2 switches in the Cisco AI POD reference architecture.

Enquire with XS Network Tech for new or used pricing and availability.

Features

- Fixed-configuration AI training server with a single defined build
- NVIDIA HGX H100 8-GPU baseboard with SXM GPUs
- 400G east-west networking through eight ConnectX-7 adapters for GPU-to-GPU scale-out
- BlueField-3 B3220 NIC for storage and front-end traffic
- Dual 4th Gen AMD EPYC 9554 processors
- Redundant power with 4+2 on the 54V supplies and 80 PLUS Titanium efficiency
- Host BMC via DC-SCM module with IPMI 2.0 and KVM
- Fits Cisco AI POD and NVIDIA Enterprise Reference Architecture designs

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

- Form factor: 8RU rack server, fixed configuration
- GPU: 8 x NVIDIA HGX H100 SXM (UBB GPU sled)
- CPU: 2 x AMD EPYC 9554, 3.1 GHz (up to 3.75 GHz boost)
- Memory: 24 x 96GB DDR5 5600 DIMMs (2.3TB)
- Data storage: 16 x 1.92TB NVMe 2.5-inch SSD
- Boot storage: 1 x M.2 NVMe boot drive
- East-west networking: 8 x NVIDIA ConnectX-7 1x400GbE
- North-south networking: 1 x NVIDIA BlueField-3 B3220
- LAN NIC: 1 x OCP Intel X710 T2L 2x10GbE
- Management: DC-SCM card
- Power supplies: 6 x 3000W 54V AC plus 2 x 2700W 12V Titanium
- Maximum system power: approximately 12.5 kW
- Input voltage: 200-240 VAC, 50-60 Hz, 16A per PSU
- Front IO: 2 x USB 2.0, UID button, power button
- Dimensions (H x W x D): 353 x 447 x 800 mm
- Weight: approximately 120 kg
- Operating temperature: 5 to 35 C
- Non-operating temperature: -40 to 70 C
- Operating humidity: 8% to 90% non-condensing
- EMC: FCC Class A, CISPR 32 / EN55032, CISPR 24 / EN55024, AS/NZS CISPR 32

FAQs

Q: Does this server need an operating licence?
A: The hardware itself does not require an operating licence. NVIDIA AI Enterprise software and Cisco Intersight management are separate offerings.

Q: What power does the UCSC-885A-M8-H11 need?
A: It uses six 3000W 54V AC supplies (4+2 redundant) plus two 2700W 12V Titanium supplies. Maximum system power is approximately 12.5 kW from a 200-240 VAC supply.

Q: What network switches is it designed to work with?
A: It is designed for the Cisco AI POD reference architecture alongside Cisco Nexus 9364E-SG2 switches and NVIDIA ConnectX-7 and BlueField-3 networking.

Q: How does the H11 differ from other C885A M8 models?
A: The H11 uses H100 GPUs with eight ConnectX-7 400GbE NICs, one BlueField-3 B3220 and 2.3TB of memory. Other C885A M8 PIDs vary the GPU type and networking configuration.

Q: Can the configuration be changed?
A: No. Each C885A M8 PID identifies a single fixed configuration, so the GPUs, CPUs, memory and NICs are as specified.

  • 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