NVIDIA A2 vs NVIDIA H100 SXM
How the NVIDIA A2 and NVIDIA H100 SXM compare across memory, compute, power and form factor, with the stronger figure highlighted on each row.
| Specification |
AMPERE
NVIDIA A2
View Product →
|
HOPPER
NVIDIA H100 SXM
View Product →
|
|---|---|---|
| Pricing | ||
| Price | – | – |
| Overview | ||
| Architecture | Ampere | Hopper |
| Memory | ||
| Memory | 16 GB GDDR6 with ECC | 80 GB HBM3 |
| Memory Bandwidth | 200 GB/s | 3.35 TB/s |
| Compute | ||
| CUDA Cores | 1,280 | – |
| Tensor Cores | 40 | – |
| RT Cores | 10 | – |
| FP32 | 4.5 TFLOPS | 67 TFLOPS |
| FP64 Tensor | – | 67 TFLOPS |
| TF32 Tensor | 9 TFLOPS (18 TFLOPS with sparsity) | 989 TFLOPS |
| FP16/BF16 Tensor | – | 1,979 TFLOPS |
| FP8 Tensor | – | 3,958 TFLOPS |
| INT8 Tensor | – | 3,958 TOPS |
| Platform | ||
| Interface | PCIe Gen4 x8 | Gen5 128 GB/s |
| NVLink | – | 900 GB/s (4th Gen) |
| TDP | 40–60W (configurable) | Up to 700W (configurable) |
| Form Factor | Low-profile, single-slot, passive | SXM |
| Multi-Instance GPU (MIG) | – | Up to 7 instances (10GB each) |
Not sure which fits?
Talk to an Expert →
Talk it through with a specialist
Tell us your workload and we will recommend the right GPU, configuration, and sourcing options.