NVIDIA H100 vs NVIDIA V100
Side-by-side comparison of specifications, performance, and efficiency.
NVIDIA H100
Architecture
Hopper
Year
2022
VRAM
80 GB
TDP
350 W
NVIDIA V100
Architecture
Volta
Year
2018
VRAM
32 GB
TDP
300 W
Specifications
NVIDIA H100 NVIDIA V100
Architecture
Hopper Volta
Launch Year
2022 2018
Form Factor
PCIe SXM
VRAM
80 GB32 GB
Memory Bandwidth
2.0 TB/s900 GB/s
TDP
350 W300 W
Process Node
4nm 12nm
| Spec | NVIDIA H100 | NVIDIA V100 |
|---|---|---|
| Architecture | Hopper | Volta |
| Launch Year | 2022 | 2018 |
| Form Factor | PCIe | SXM |
| VRAM | 80 GB | 32 GB |
| Memory Bandwidth | 2.0 TB/s | 900 GB/s |
| TDP | 350 W | 300 W |
| Process Node | 4nm | 12nm |
Performance (TFLOPS)
NVIDIA H100 NVIDIA V100
FP64
26.0 TFlops7.8 TFlops
FP32
51.0 TFlops15.7 TFlops
FP16
756.5 TFlops125.0 TFlops
BF16
756.5 TFlops—
FP8
1513.0 TFlops—
INT8
1513.0 TFlops—
| Precision | NVIDIA H100 | NVIDIA V100 |
|---|---|---|
| FP64 | 26.0 TFlops | 7.8 TFlops |
| FP32 | 51.0 TFlops | 15.7 TFlops |
| FP16 | 756.5 TFlops | 125.0 TFlops |
| BF16 | 756.5 TFlops | — |
| FP8 | 1513.0 TFlops | — |
| INT8 | 1513.0 TFlops | — |
FLOPS by Precision
Efficiency — TDP vs FP32 Performance
Analysis
Most Efficient
NVIDIA
H100
0.15 TFLOPS/W
Get Comparison Updates
New GPUs added weekly. Be the first to see how they compare.