Skip to product information
1 of 1

Cisco

Cisco HX-GPU-A100-80 | PCIe Gen4 x16 | Passive | 80GB HBM2e ECC | 300W TDP | Ampere Tensor GPU (MIG-capable)

SKU:HX-GPU-A100-80

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

Description

Top-tier Ampere Tensor GPU for large-scale AI training, inference, and HPC with massive 80GB HBM2e memory. Passive PCIe design requires robust server airflow and power. Supports MIG for secure, efficient multi-tenant utilization.

Features

- 80GB HBM2e ECC for the largest training workloads
- MIG for secure multi-tenant GPU sharing
- Passive PCIe FHFL design for dense server deployments
- 3rd-gen Tensor Cores deliver leading AI performance
- PCIe Gen4 x16 connectivity
- Robust enterprise software and driver stack

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 power and cooling are required?
A: Plan for 300 W per GPU and ensure high-throughput front-to-back airflow in a supported OEM server chassis.

Q: Is MIG available on this model?
A: Yes. MIG allows partitioning the GPU into multiple isolated instances for improved utilization.

Q: Are brackets or bridges included?
A: No, the card ships without additional accessories unless specified.

Q: Which frameworks are supported?
A: Common AI frameworks (PyTorch, TensorFlow, RAPIDS) are supported via NVIDIA Data Center drivers and CUDA libraries.

Q: Can this be used in workstations?
A: It is a passive, server-focused card and is generally not suitable for open-air workstations without engineered airflow.

Technical Specifications

- GPU architecture: NVIDIA Ampere (A100)
- Interface: PCIe 4.0 x16
- Cooling: Passive heatsink (requires strong chassis airflow)
- Memory: 80 GB HBM2e with ECC
- Thermal design power (TDP): 300 W
- Form factor: Full-height, full-length (FHFL)
- Capabilities: 3rd-gen Tensor Cores, TF32/FP16/INT8 acceleration
- MIG support: Yes (Multi-Instance GPU)
- Workloads: Large-model training, inference at scale, HPC
- 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