NVIDIA DGX Spark vs NVIDIA GeForce RTX 3080 Ti
Side-by-side comparison of specifications, performance, and efficiency.
NVIDIA DGX Spark
Architecture
Grace Blackwell
Year
2025
VRAM
128 GB
TDP
240 W
NVIDIA GeForce RTX 3080 Ti
Architecture
Ampere
Year
2021
VRAM
12 GB
TDP
350 W
Specifications
NVIDIA DGX Spark NVIDIA GeForce RTX 3080 Ti
Architecture
Grace Blackwell Ampere
Launch Year
2025 2021
Form Factor
Desktop Workstation PCIe
VRAM
128 GB12 GB
Memory Bandwidth
273 GB/s912 GB/s
TDP
240 W350 W
Process Node
4nm 8nm
| Spec | NVIDIA DGX Spark | NVIDIA GeForce RTX 3080 Ti |
|---|---|---|
| Architecture | Grace Blackwell | Ampere |
| Launch Year | 2025 | 2021 |
| Form Factor | Desktop Workstation | PCIe |
| VRAM | 128 GB | 12 GB |
| Memory Bandwidth | 273 GB/s | 912 GB/s |
| TDP | 240 W | 350 W |
| Process Node | 4nm | 8nm |
Performance (TFLOPS)
NVIDIA DGX Spark NVIDIA GeForce RTX 3080 Ti
FP64
—0.5 TFlops
FP32
—34.1 TFlops
FP16
100.0 TFlops34.1 TFlops
BF16
—34.1 TFlops
INT8
—68.2 TFlops
| Precision | NVIDIA DGX Spark | NVIDIA GeForce RTX 3080 Ti |
|---|---|---|
| FP64 | — | 0.5 TFlops |
| FP32 | — | 34.1 TFlops |
| FP16 | 100.0 TFlops | 34.1 TFlops |
| BF16 | — | 34.1 TFlops |
| INT8 | — | 68.2 TFlops |
FLOPS by Precision
Efficiency — TDP vs FP32 Performance
Analysis
Most Efficient
NVIDIA
GeForce RTX 3080 Ti
0.10 TFLOPS/W
Get Comparison Updates
New GPUs added weekly. Be the first to see how they compare.