Skip to product information
1 of 1

Cisco

Cisco UCSC-885A-M8-HC1 | UCS C885A M8 8RU GPU Server, H200, 3TB Memory

SKU:UCSC-885A-M8-HC1

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 We do not quote Gmail, Outlook or Hotmail addresses, or supply for home use. 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 rack server built on the NVIDIA HGX reference architecture, designed for dense AI workloads. It suits large language model training, fine-tuning, large-model inference and retrieval augmented generation (RAG), and it serves as the compute node in the Cisco Nexus Hyperfabric AI enterprise reference architecture.

This configuration pairs an H200 GPU platform with 8x NVIDIA BlueField-3 B3140H and 2x NVIDIA BlueField-3 B3240 adapters and 3TB of system memory. The Cisco variant provides 2x 400G frontend ports in place of NVIDIA's reference 2x 200G, and the x86 management ports run at 10G rather than the 1G reference.

When deployed within the Nexus Hyperfabric AI reference architecture, note that the VAST storage solution requires a minimum of 8x 400G connectivity to the storage network.

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

Features

- Dense 8RU GPU server for LLM training, fine-tuning, large-model inference and RAG
- Built on the NVIDIA HGX reference architecture
- 2x 400G frontend ports rather than NVIDIA's reference 2x 200G
- 10G x86 management ports rather than 1G
- Compute server in the Cisco Nexus Hyperfabric AI enterprise reference architecture
- BlueField-3 DPU BMC ports are connected, while SuperNIC BMC ports are managed from the x86 host

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
- Platform: NVIDIA HGX, 2-8-10-400 (C-G-N-B) configuration
- GPU: H200
- Adapters: 8x NVIDIA BlueField-3 B3140H
- Adapters: 2x NVIDIA BlueField-3 B3240
- System memory: 3TB
- Frontend ports: 2x 400G
- Management ports: 10G x86

FAQs

Q: What workloads is the UCS C885A M8 designed for?
A: It is built for AI workloads such as LLM training, fine-tuning, large-model inference and retrieval augmented generation (RAG).

Q: How does this SKU differ from other C885A M8 configurations?
A: This configuration is specified with an H200 GPU platform, 8x BlueField-3 B3140H, 2x BlueField-3 B3240 and 3TB of system memory.

Q: Does it work with Cisco Nexus Hyperfabric?
A: Yes. It is listed as the compute server in the Cisco Nexus Hyperfabric AI enterprise reference architecture.

Q: What storage network connectivity is needed with VAST storage?
A: The VAST storage solution requires a minimum of 8x 400G to the storage network.

  • 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