NVIDIA A30 24GB vs NVIDIA H100 SXM
A30 24GB has 70% less memory than H100 SXM (24 GB vs 80 GB). Its memory bandwidth is 72% less (0.933 vs 3.35 TB/s). In the cloud, the median on-demand A30 24GB price is $0.41 per GPU-hour against $3.90 for the H100 SXM. Per gigabyte of GPU memory, that is $0.017 vs $0.049 per hour.
Specifications
Manufacturer figures as recorded by Kovara. Higher memory and bandwidth are highlighted; neither is a benchmark of your workload.
| A30 24GB | H100 SXM | |
|---|---|---|
| Manufacturer | NVIDIA | NVIDIA |
| Architecture | Ampere | Hopper |
| Memory | 24 GB HBM2 | 80 GB HBM3 |
| Memory bandwidth | 0.933 TB/s | 3.35 TB/s |
| Power (TDP) | 165 W | 700 W |
| Form factor | PCIe dual-slot FHFL | SXM |
Cloud prices today
Public offers Kovara tracks, normalised to US dollars per GPU-hour. Prices use on-demand terms where available; spot and reserved offers are on each GPU’s price pages. Lower is highlighted.
| A30 24GB | H100 SXM | |
|---|---|---|
| Lowest price | $0.35 | $1.99 |
| Median price | $0.41 | $3.90 |
| Highest price | $1.35 | $12.29 |
| Median per GB of memory | $0.017 | $0.049 |
| Public offers (all terms) | 9 | 61 |
| Providers | 3 | 22 |
Where to rent each
Lowest tracked price per provider. Open a provider to see every offer, region and term.
Questions
Which is cheaper to rent, the A30 24GB or the H100 SXM?
Right now the cheapest on-demand A30 24GB Kovara tracks is $0.35 per GPU-hour and the cheapest H100 SXM is $1.99. Medians are $0.41 and $3.90. The cheaper GPU per hour is not always cheaper per job: a faster or larger GPU can finish sooner or need fewer units.
Which has more memory?
The H100 SXM has more memory: 80 GB against 24 GB. Memory decides which models and batch sizes fit on one GPU.
Are these benchmark results?
No. This page compares manufacturer specifications and public prices. Real performance depends on the model, precision, software and interconnect. Kova can help you estimate cost for a specific workload.