Skip to product information
1 of 1

Cisco

Cisco HX-GPU-A100 | PCIe Gen4 x16 | Passive | 40GB HBM2 ECC | 250W TDP | Ampere Tensor GPU (MIG-capable)

SKU:HX-GPU-A100

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

Description

High-performance Ampere Tensor GPU for AI training/inference and HPC. PCIe passive design for OEM servers with strong front-to-back airflow. Supports MIG for workload isolation and efficient GPU sharing.

Features

- Ampere Tensor Cores for state-of-the-art AI acceleration
- 40GB HBM2 ECC memory for large models and datasets
- MIG enables secure, isolated GPU partitions
- Passive PCIe design for dense data center deployments
- PCIe Gen4 bandwidth for high-throughput IO
- Enterprise driver ecosystem and broad framework support

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
  • You may also like
  • Best sellers
  • Related Products

specs-tabs

Collapsible content

FAQs

Technical Specifications

FAQs

Q: What are the chassis requirements?
A: A server with front-to-back airflow, adequate PCIe 4.0 x16 slot clearance, and at least 250 W per card from the PSU is required.

Q: Does this card support MIG?
A: Yes. It supports Multi-Instance GPU to partition the GPU into isolated instances for concurrent workloads.

Q: Are NVLink bridges included?
A: No accessories are included unless explicitly stated.

Q: Which drivers should I use?
A: Use NVIDIA Data Center drivers appropriate for your OS; for containerized workloads, NVIDIA Container Toolkit is supported.

Q: Can I mix this with different GPU models?
A: For deterministic performance and supportability, avoid mixing dissimilar GPU architectures or memory sizes in the same node.

Technical Specifications

- GPU architecture: NVIDIA Ampere (A100)
- Interface: PCIe 4.0 x16
- Cooling: Passive heatsink (server airflow required)
- Memory: 40 GB HBM2 with ECC
- Thermal design power (TDP): 250 W
- Form factor: Full-height, full-length (FHFL)
- Capabilities: 3rd-gen Tensor Cores, TF32/FP16/INT8 acceleration
- MIG support: Yes (Multi-Instance GPU)
- Workloads: AI training, inference, HPC, data analytics
- Driver support: NVIDIA Data Center (Linux/Windows)

Recently Viewed

  • Request for 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