- Home
- Compare GPUs
- NVIDIA GB200 vs NVIDIA GeForce RTX 5090
NVIDIA GB200 vs NVIDIA GeForce RTX 5090
Side-by-side comparison of specifications, performance, and efficiency.
NVIDIA GB200
Architecture
Blackwell
Year
2024
VRAM
372 GB
NVIDIA GeForce RTX 5090
Architecture
Blackwell
Year
2025
VRAM
32 GB
TDP
575 W
Specifications
NVIDIA GB200 NVIDIA GeForce RTX 5090
Architecture
Blackwell Blackwell
Launch Year
2024 2025
Form Factor
Superchip PCIe
VRAM
372 GB32 GB
Memory Bandwidth
16.0 TB/s1.8 TB/s
TDP
—575 W
Process Node
4nm 4nm
| Spec | NVIDIA GB200 | NVIDIA GeForce RTX 5090 |
|---|---|---|
| Architecture | Blackwell | Blackwell |
| Launch Year | 2024 | 2025 |
| Form Factor | Superchip | PCIe |
| VRAM | 372 GB | 32 GB |
| Memory Bandwidth | 16.0 TB/s | 1.8 TB/s |
| TDP | — | 575 W |
| Process Node | 4nm | 4nm |
Performance (TFLOPS)
NVIDIA GB200 NVIDIA GeForce RTX 5090
FP64
80.0 TFlops1.6 TFlops
FP32
160.0 TFlops104.8 TFlops
FP16
5000.0 TFlops419.1 TFlops
BF16
5000.0 TFlops419.1 TFlops
FP8
10000.0 TFlops838.2 TFlops
INT8
10000.0 TFlops838.2 TFlops
| Precision | NVIDIA GB200 | NVIDIA GeForce RTX 5090 |
|---|---|---|
| FP64 | 80.0 TFlops | 1.6 TFlops |
| FP32 | 160.0 TFlops | 104.8 TFlops |
| FP16 | 5000.0 TFlops | 419.1 TFlops |
| BF16 | 5000.0 TFlops | 419.1 TFlops |
| FP8 | 10000.0 TFlops | 838.2 TFlops |
| INT8 | 10000.0 TFlops | 838.2 TFlops |
FLOPS by Precision
Efficiency — TDP vs FP32 Performance
Analysis
Most Efficient
NVIDIA
GeForce RTX 5090
0.18 TFLOPS/W
Where to Rent
NVIDIA GeForce RTX 5090
| Provider | Instance | Price/hr | |
|---|---|---|---|
RunPod | RTX 5090 | $0.69 | View → |
Get Comparison Updates
New GPUs added weekly. Be the first to see how they compare.