NVIDIA A100 vs NVIDIA GeForce RTX 3090
Side-by-side comparison of specifications, performance, and efficiency.
NVIDIA A100
Architecture
Ampere
Year
2020
VRAM
40 GB
TDP
250 W
NVIDIA GeForce RTX 3090
Architecture
Ampere
Year
2020
VRAM
24 GB
TDP
350 W
Specifications
NVIDIA A100 NVIDIA GeForce RTX 3090
Architecture
Ampere Ampere
Launch Year
2020 2020
Form Factor
PCIe PCIe
VRAM
40 GB24 GB
Memory Bandwidth
1.6 TB/s936 GB/s
TDP
250 W350 W
Process Node
7nm 8nm
| Spec | NVIDIA A100 | NVIDIA GeForce RTX 3090 |
|---|---|---|
| Architecture | Ampere | Ampere |
| Launch Year | 2020 | 2020 |
| Form Factor | PCIe | PCIe |
| VRAM | 40 GB | 24 GB |
| Memory Bandwidth | 1.6 TB/s | 936 GB/s |
| TDP | 250 W | 350 W |
| Process Node | 7nm | 8nm |
Performance (TFLOPS)
NVIDIA A100 NVIDIA GeForce RTX 3090
FP64
9.7 TFlops0.6 TFlops
FP32
19.5 TFlops35.6 TFlops
FP16
312.0 TFlops35.6 TFlops
BF16
312.0 TFlops35.6 TFlops
INT8
624.0 TFlops71.2 TFlops
| Precision | NVIDIA A100 | NVIDIA GeForce RTX 3090 |
|---|---|---|
| FP64 | 9.7 TFlops | 0.6 TFlops |
| FP32 | 19.5 TFlops | 35.6 TFlops |
| FP16 | 312.0 TFlops | 35.6 TFlops |
| BF16 | 312.0 TFlops | 35.6 TFlops |
| INT8 | 624.0 TFlops | 71.2 TFlops |
FLOPS by Precision
Efficiency — TDP vs FP32 Performance
Analysis
Most Efficient
NVIDIA
GeForce RTX 3090
0.10 TFLOPS/W
Get Comparison Updates
New GPUs added weekly. Be the first to see how they compare.