NVIDIA · Ampere
A10G 24 GB (AWS) rental prices and specifications
The AWS G5-specific A10G GPU, advertised with 24 GB memory. AWS instance documentation lists 22 GiB usable GPU memory; it is distinct from the standard A10 card. Exact A10G bandwidth and dense tensor peaks remain unverified.
Profile checked · Primary source ↗
- Memory
- 24 GB
- Bandwidth
- —
- Current offers
- 0
- FP16 dense
- Not published
- BF16 dense
- Not published
- FP8 dense
- Not verified
- Interconnect
- Not verified
Compare A10G 24 GB (AWS) cloud rentals
Use the exact 24 GB GPU profile when comparing rental quotes. Tables separate currencies, billing periods and rental terms; the required GPU count determines the whole-instance compute cost. Storage, transfer, taxes and other charges can be additional.
Source checks show when each price was actually observed. Historical quotes remain available separately and do not enter current price comparisons. Explore the sourced GPU rental price index or check a rental against your model requirements.
Recently checked listings
Current rental offers
| GPU / provider | Instance price / offer | Terms / location |
|---|---|---|
| No offers match these filters. Try another billing period or currency. | ||
Previously observed offers
1 retained quote with an old check, a different allocation, or unavailable status. These are excluded from current prices and capacity counts.
Hide previously observed offers
USD · Hourly · On-demand
| GPU / provider | Instance price / offer | Terms / location |
|---|---|---|
| A10G 24 GB (AWS) Amazon Web Services g5.xlarge Linux shared 24 GB per GPU · 1 GPU per instance | Previously observed quote USD 1.01/hr per instanceUSD 1.01 /hr per GPU Browse Amazon Web Services Details & price history Pricing evidence (large JSON download) Readable pricing page Stale — recheck |
HourlyOn-demand
No monthly commitment
Stock not verified · United States · us-east-1
AWS EC2
Billing & region detailsOn-demand Linux shared tenancy; no monthly commitment. 60-second minimum. Capacity is not verified. |
Prices and availability can change. Confirm the current offer with the provider. Taxes and extra services are additional.
Measured performance
Inference benchmarks
| Model | GPU setup | Engine | Quant. | Workload | Reported tok/s | Evidence | Max-load capacity scenarioUSD / million output tokens |
|---|---|---|---|---|---|---|---|
| No benchmark records have been supplied yet. | |||||||