- Home
- Compare GPUs
- NVIDIA A100 vs NVIDIA GeForce RTX 5090
NVIDIA A100 vs NVIDIA GeForce RTX 5090
Side-by-side comparison of specifications, performance, and efficiency.
NVIDIA A100
OfficialArchitecture
Ampere
Year
2020
VRAM
80 GB
TDP
400 W
NVIDIA GeForce RTX 5090
OfficialArchitecture
Blackwell
Year
2025
VRAM
32 GB
TDP
575 W
Specifications
NVIDIA A100 NVIDIA GeForce RTX 5090
Architecture
Ampere Blackwell
Launch Year
2020 2025
Form Factor
SXM PCIe
VRAM
80 GB32 GB
Memory Bandwidth
2.0 TB/s1.8 TB/s
TDP
400 W575 W
Process Node
7nm 4nm
| Spec | NVIDIA A100 | NVIDIA GeForce RTX 5090 |
|---|---|---|
| Architecture | Ampere | Blackwell |
| Launch Year | 2020 | 2025 |
| Form Factor | SXM | PCIe |
| VRAM | 80 GB | 32 GB |
| Memory Bandwidth | 2.0 TB/s | 1.8 TB/s |
| TDP | 400 W | 575 W |
| Process Node | 7nm | 4nm |
Performance (TFLOPS)
NVIDIA A100 NVIDIA GeForce RTX 5090
FP64
9.7 TFlops1.6 TFlops
FP32
19.5 TFlops104.8 TFlops
FP16
312.0 TFlops419.1 TFlops
BF16
312.0 TFlops419.1 TFlops
FP8
—838.2 TFlops
INT8
624.0 TFlops838.2 TFlops
| Precision | NVIDIA A100 | NVIDIA GeForce RTX 5090 |
|---|---|---|
| FP64 | 9.7 TFlops | 1.6 TFlops |
| FP32 | 19.5 TFlops | 104.8 TFlops |
| FP16 | 312.0 TFlops | 419.1 TFlops |
| BF16 | 312.0 TFlops | 419.1 TFlops |
| FP8 | — | 838.2 TFlops |
| INT8 | 624.0 TFlops | 838.2 TFlops |
FLOPS by Precision
Efficiency — TDP vs FP32 Performance
Analysis
Most Efficient
NVIDIA
GeForce RTX 5090
0.18 TFLOPS/W
Get Comparison Updates
New GPUs added weekly. Be the first to see how they compare.