Skip to product information
1 of 1

Cisco

Cisco HCIX-GPU-A100-80 | PCIe 4.0 x16 | 80GB HBM2e | 300W passive | Tensor Core GPU with MIG

SKU:HCIX-GPU-A100-80

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

Description

Ampere Tensor Core GPU engineered for large-scale AI training and inference, advanced analytics, and HPC acceleration. 80GB of high-bandwidth HBM2e memory and PCIe 4.0 deliver exceptional throughput, while MIG partitions enable secure multi-tenant workloads on a single card. Passive 300W design integrates into qualified servers with data center airflow for reliable performance at scale. Ideal for AI/ML pipelines, model serving, and mixed-precision computing in enterprise environments.

Features

- 80GB HBM2e for large-model AI and HPC
- MIG for secure, multi-tenant GPU consolidation
- Advanced Tensor Cores accelerate mixed-precision AI
- PCIe 4.0 bandwidth for fast data ingestion
- Enterprise-ready reliability with ECC and server-grade design

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: Will this work in my server?
A: Requires a qualified PCIe 4.0 x16 slot, 300W power budget, and chassis airflow for passive cooling. Check your server’s BOM and GPU qualification guide.

Q: Does it have video outputs for monitors?
A: No. It is a data center accelerator without display outputs.

Q: Is NVIDIA vGPU licensing required?
A: Only if you plan to virtualize the GPU across multiple VMs/users. Bare-metal and containerized workloads do not require vGPU licenses.

Q: What is MIG and do I have to use it?
A: MIG partitions the GPU into up to seven isolated instances. It is optional—use full-GPU mode when maximum single-job performance is needed.

Q: Active vs passive cooling?
A: This is a passive card; it relies on server chassis fans for cooling. Ensure adequate airflow per the server integration guide.

Technical Specifications

- GPU architecture: NVIDIA Ampere Tensor Core
- Memory: 80GB HBM2e, high bandwidth for large models and datasets
- Interface: PCIe 4.0 x16
- Thermal design power: 300W (passive, server airflow required)
- Form factor: full-height, dual-slot passive accelerator
- Multi-Instance GPU (MIG): up to 7 isolated GPU instances
- ECC memory: supported
- Compute precision: FP64/FP32/TF32/FP16/bfloat16/INT8/INT4 with sparsity acceleration
- Display outputs: none (data center accelerator)
- Virtualization: supports NVIDIA vGPU software (licensed) for multi-tenant use

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