NVIDIA A800 PCIe 80GB
Overview
China export variant of A100 PCIe 80GB. Identical compute, NVLink reduced to 400 GB/s.
Performance
Peak theoretical throughput by precision type
The A800 PCIe 80GB in the GPU landscape
Peak FP16 TFLOPS (dense) against TDP, single-GPU parts tracked by Flopper
Higher and further left is better: more half-precision throughput for less power.
Specifications
Architecture
Ampere
Form Factor
PCIe
Launch Year
2022
Process Node
7nm
Memory
80 GB HBM2e
Bandwidth
1,935 GB/s
TDP
300 W
Max Power
~345 W
Spec Confidence
Official
Full Specifications
| Memory | |
|---|---|
| VRAM | 80 GB |
| Memory Type | HBM2e |
| Bandwidth | 1.9 TB/s |
| Power & Thermal | |
| TDP | 300 W |
| Enterprise Features | |
| Sparsity | Yes |
| General | |
| Form Factor | PCIe |
| Architecture | Ampere |
| Launch Year | 2022 |
Datasheet & Resources
Flopper Datasheet
NVIDIA A800 PCIe 80GB specifications, generated from our database. Printable.
NVIDIA Developer Documentation
Technical specs, programming guides
Data Provenance
Every figure traced to a source
Primary Source
- Document
- --
- Publisher
- NVIDIA
- Published
- --
Data Quality
- Spec confidence
- Official
- Clock basis
- Boost
- Precisions tracked
- 7
- Normalization
- All values in TFLOPS
Compare cloud providers offering on-demand GPU instances for AI training, inference, and HPC workloads.
Browse GPU Cloud ProvidersSimilar GPUs
Frequently Asked Questions
How many TFLOPS does the NVIDIA A800 have?
The NVIDIA A800 delivers 19.5 TFLOPS for FP32 operations, 312 TFLOPS for FP16, and N/A TFLOPS for FP8 precision.
What is the power consumption of the NVIDIA A800?
The NVIDIA A800 has a TDP (Thermal Design Power) rating of 300 watts.
How much memory does the NVIDIA A800 have?
The NVIDIA A800 is equipped with 80 GB of VRAM with 1935 GB/s memory bandwidth.
What architecture is the NVIDIA A800 based on?
The NVIDIA A800 is based on the Ampere architecture, launched in 2022.
Stay Updated on GPU Releases
Get notified when new GPUs are added or specifications are updated.
No spam, unsubscribe anytime.