NVIDIA H100 vs NVIDIA RTX A6000
Side-by-side comparison of specifications, performance, and efficiency.
NVIDIA H100
Architecture
Hopper
Year
2022
VRAM
80 GB
TDP
700 W
NVIDIA RTX A6000
Architecture
Ampere
Year
2020
VRAM
48 GB
TDP
300 W
Specifications
NVIDIA H100 NVIDIA RTX A6000
Architecture
Hopper Ampere
Launch Year
2022 2020
Form Factor
SXM PCIe
VRAM
80 GB48 GB
Memory Bandwidth
3.4 TB/s768 GB/s
TDP
700 W300 W
Process Node
4nm 8nm
| Spec | NVIDIA H100 | NVIDIA RTX A6000 |
|---|---|---|
| Architecture | Hopper | Ampere |
| Launch Year | 2022 | 2020 |
| Form Factor | SXM | PCIe |
| VRAM | 80 GB | 48 GB |
| Memory Bandwidth | 3.4 TB/s | 768 GB/s |
| TDP | 700 W | 300 W |
| Process Node | 4nm | 8nm |
Performance (TFLOPS)
NVIDIA H100 NVIDIA RTX A6000
FP64
34.0 TFlops0.6 TFlops
FP32
67.0 TFlops38.7 TFlops
FP16
989.5 TFlops38.7 TFlops
BF16
989.5 TFlops38.7 TFlops
FP8
1979.0 TFlops—
INT8
1979.0 TFlops77.4 TFlops
| Precision | NVIDIA H100 | NVIDIA RTX A6000 |
|---|---|---|
| FP64 | 34.0 TFlops | 0.6 TFlops |
| FP32 | 67.0 TFlops | 38.7 TFlops |
| FP16 | 989.5 TFlops | 38.7 TFlops |
| BF16 | 989.5 TFlops | 38.7 TFlops |
| FP8 | 1979.0 TFlops | — |
| INT8 | 1979.0 TFlops | 77.4 TFlops |
FLOPS by Precision
Efficiency — TDP vs FP32 Performance
Analysis
Most Efficient
NVIDIA
RTX A6000
0.13 TFLOPS/W
Get Comparison Updates
New GPUs added weekly. Be the first to see how they compare.