The NVIDIA DGX A100 is the universal system for all AI workloads, offering unprecedented compute density, performance, and flexibility in the world's first 5-petaFLOPS AI system. Built on the NVIDIA Ampere architecture, it integrates eight NVIDIA A100 Tensor Core GPUs to provide a unified platform for training, inference, and data analytics.
- Features 8x NVIDIA A100 Tensor Core GPUs with a total of 320GB of HBM2 memory.
- Delivers 5 petaFLOPS of AI performance and 10 petaOPS of INT8 performance.
- Powered by dual AMD EPYC 7742 processors providing 128 total cores at 2.25GHz.
- Includes 1TB of DDR4 system memory for massive dataset handling.
- Equipped with 15TB of high-performance NVMe internal storage.
- Utilizes NVIDIA NVLink and NVSwitch for 600GB/s GPU-to-GPU bandwidth.
- Features 9x Mellanox ConnectX-6 200Gb/s network interfaces for high-speed clustering.
- Supports Multi-Instance GPU (MIG) technology to partition GPUs into 56 instances.
- Optimized for the NVIDIA DGX software stack including AI frameworks and containers.
- Standard 6U rackmount form factor designed for enterprise data center deployment.
NVIDIA
NVIDIA - DGX A100 (8x A100 40GB) - AI Infrastructure Supercomputer
For a quote, contact us at info@tropical.com
- SKU:
- DGX A100 (8x A100 40GB)
- Weight:
- 271.17 LBS
- Width:
- 19.00 (in)
- Height:
- 10.40 (in)
- Depth:
- 35.30 (in)
Related Products
A relatable product
NVIDIA
NVIDIA - DGX A100 (8x A100 80GB) - AI Infrastructure System
The NVIDIA DGX A100 is the universal system for all AI workloads, offering unprecedented compute density, performance, and flexibility in the world's first 5-petaFLOPS AI system. Featuring eight...
NVIDIA
NVIDIA - DGX A100 Enterprise Config - AI Infrastructure Supercomputer
The NVIDIA DGX A100 is the foundational building block for enterprise AI, delivering the world’s first 5-petaFLOPS system in a single 6U form factor. It integrates eight NVIDIA A100 Tensor Core GPUs...
NVIDIA - DGX A100 - AI Infrastructure System
The NVIDIA DGX A100 is the universal system for all AI workloads, offering unprecedented compute density, performance, and flexibility in the world's first 5-petaFLOPS AI system. It integrates eight...
NVIDIA - DGX SuperPOD (A100) - AI Data Center Infrastructure
The NVIDIA DGX SuperPOD is a turnkey AI data center solution designed to provide leadership-class infrastructure for the most challenging AI training and inference workloads. It integrates...
NVIDIA
NVIDIA - DGX A100 640GB Config - AI Infrastructure System
The NVIDIA DGX A100 is the universal system for all AI workloads, offering unprecedented compute density, performance, and flexibility in the world's first 5-petaFLOPS AI system. Featuring eight...