A100 PCIe 40 GB

Key Metrics

Launch Date
2020-06-22
CUDA Cores
6,912
Memory
40 GB HBM2
Memory Bandwidth
1,560 GB/s
TDP/TBP
250 W
Interface
PCIe 4.0 x16
Add to comparison

Save this GPU, then open another GPU page to compare them side by side.

Why It Mattered

A100 PCIe 40 GB matters because A100 was part of NVIDIA's Ampere data-center push into AI, HPC, analytics, and multi-instance GPU deployment. Tracking the PCIe, SXM, and memory variants separately helps readers avoid mixing very different server form factors.

Sources

Primary / manufacturer sources

  1. NVIDIA A100 40 GB PCIe GPU Accelerator product brief PB-10137-001 v03Official memory, interface, total board power, and connector specificationsOpen source
  2. World's Top System Makers Unveil NVIDIA A100-Powered Servers to Accelerate AI, Data Science and Scientific ComputingOfficial June 22, 2020 unveiling of the A100 PCIe form factorOpen source

Independent reference sources

  1. TechPowerUp GPU SpecsModel-level specification reference for this GPU entryOpen source

Reference databases

  1. RightNow GPU DatabaseOpen GPU database used to cross-check specifications A reference database: good for cross-checking specifications, but not proof of the original release details on its own.Open source