H100 PCIe vs A100 PCIe: GPU cloud servers compared in Canada
H100 PCIe from $3.35/h (1 GPU), A100 PCIe from $1.81/h (1 GPU). Memory, interconnect, server sizes and hourly prices in Canadian dollars, servers hosted in Canada.
Specs and prices
| Criterion | NVIDIA H100 PCIe | NVIDIA A100 PCIe |
|---|---|---|
| Memory per GPU | 80 GB HBM2e | 80 GB HBM2e |
| Interconnect | PCIe Gen5 | PCIe Gen4 |
| CUDA cores | 14,592 | 6,912 |
| Tensor cores | 456 | 432 |
| Power (TDP) | 350W | 300W |
| GPUs per server | 1, 2, 4 or 8 | 1, 2, 4 or 8 |
| On-demand price | from $3.35/h (1 GPU) | from $1.81/h (1 GPU) |
| Spot price (interruptible) | $2.68/h | $1.45/h |
Public hourly prices in Canadian dollars (CAD), taxes extra. Specs as published by NVIDIA.
In short
- Both models have 80 GB HBM2e of memory per GPU.
- The A100 PCIe starts at $1.81/h, the H100 PCIe at $3.35/h (public hourly prices, in Canadian dollars, taxes extra).
H100 PCIe use cases
- LLM training and fine-tuning
- Large-scale LLM inference
- Scientific computing (HPC)
A100 PCIe use cases
- Model training and fine-tuning
- High-performance LLM inference
- Scientific computing (HPC)
Frequently asked questions
What is the price difference between the H100 PCIe and the A100 PCIe?
H100 PCIe: from $3.35/h (1 GPU). A100 PCIe: from $1.81/h (1 GPU). Prices in Canadian dollars, taxes extra, hourly billing with no commitment.
How many GPUs per server for the H100 PCIe and the A100 PCIe?
H100 PCIe: 1, 2, 4 or 8 GPUs per server. A100 PCIe: 1, 2, 4 or 8 GPUs per server.
Where are these servers hosted?
Both models are hosted in a data centre in Canada (region canada-montreal), the only region offered.