SERVCHIP
Interactive view
ARCHITECTURE
Ampere
SERIES
A100 PCIe
Memory
80GB HBM2e
Bandwidth
2 TB/s
TDP
300W
In StockA100 PCIe·Best for: Versatile AI Acceleration (PCIe)
NVIDIA A100 PCIe Tensor Core GPU
Ampere
|Data Center GPUsOverview
The NVIDIA A100 PCIe Tensor Core GPU is the standard PCIe Gen4 form factor variant of the Ampere-architecture A100, featuring 80GB of HBM2e memory with 2 TB/s bandwidth and a 300W TDP. Designed for broad server compatibility, it fits into standard PCIe slots without requiring liquid cooling or specialized SXM infrastructure. The A100 PCIe delivers the same industry-leading Tensor Core performance for AI training, inference, and HPC workloads in a more accessible form factor.
Key Features
- 80GB HBM2e memory with 2 TB/s bandwidth
- Ampere architecture with 3rd-gen Tensor Cores
- Multi-Instance GPU (MIG) with up to 7 instances
- PCIe 4.0 x16 form factor for broad compatibility
- Passive cooling for dense server integration
Ideal Use Cases
ai trainingai inferencehpcdata analytics
Full Specifications
Complete technical specifications for the A100 PCIe.
Memory
- Memory
- 80GB HBM2e
- Memory Bandwidth
- 2 TB/s
Compute
- Tensor Cores
- 432 (3rd-gen)
- CUDA Cores
- 6912
- FP8 TFLOPS
- 624
- FP16 TFLOPS
- 312
- TF32 TFLOPS
- 156
- FP64 TFLOPS
- 19.5
Interconnect
- Interconnect
- PCIe 4.0 x16
Physical
- TDP
- 300W
- Form Factor
- PCIe Gen4
- Cooling
- Passive
Manufacturing
- Launch Date
- Q2 2020
- Manufacturing Process
- 7nm
