Kovara
Loading your page…
You can continue using the navigation while this page loads.
You can continue using the navigation while this page loads.
A100 80GB SXM has 233% more memory than A30 24GB (80 GB vs 24 GB). Its memory bandwidth is 119% more (2.039 vs 0.933 TB/s). In the cloud, the median on-demand A100 80GB SXM price is $1.69 per GPU-hour against $0.41 for the A30 24GB. Per gigabyte of GPU memory, that is $0.021 vs $0.017 per hour.
Manufacturer figures as recorded by Kovara. Higher memory and bandwidth are highlighted; neither is a benchmark of your workload.
| A100 80GB SXM | A30 24GB | |
|---|---|---|
| Manufacturer | NVIDIA | NVIDIA |
| Architecture | Ampere | Ampere |
| Memory | 80 GB HBM2E | 24 GB HBM2 |
| Memory bandwidth | 2.039 TB/s | 0.933 TB/s |
| Power (TDP) | 400 W | 165 W |
| Form factor | SXM | PCIe dual-slot FHFL |
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.
| A100 80GB SXM | A30 24GB | |
|---|---|---|
| Lowest price | $1.38 | $0.35 |
| Median price | $1.69 | $0.41 |
| Highest price | $3.18 | $1.35 |
| Median per GB of memory | $0.021 | $0.017 |
| Public offers (all terms) | 20 | 9 |
| Providers | 9 | 3 |
Lowest tracked price per provider. Open a provider to see every offer, region and term.
Right now the cheapest on-demand A100 80GB SXM Kovara tracks is $1.38 per GPU-hour and the cheapest A30 24GB is $0.35. Medians are $1.69 and $0.41. The cheaper GPU per hour is not always cheaper per job: a faster or larger GPU can finish sooner or need fewer units.
The A100 80GB SXM has more memory: 80 GB against 24 GB. Memory decides which models and batch sizes fit on one GPU.
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.