NVIDIA · Ampere
A10 rental prices and specifications
Full GPU rental listings; VRAM is nominal hardware capacity. Host-accessible memory can be lower. This profile lists observed rental offers and sourced specifications. Inference benchmarks are shown when available.
Profile checked · Primary source ↗
- Memory
- 24 GB
- Bandwidth
- 600 GB/s
- Current offers
- 0
- FP16 dense
- 125 TFLOPS
- BF16 dense
- 125 TFLOPS
- FP8 dense
- Not verified
- Interconnect
- PCIe Gen4 up to 64 GB/s.
Compare A10 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.
Manufacturer theoretical dense tensor peaks; sparsity is excluded. Application performance depends on workload, clocks and system. · Specification source 1 ↗
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
5 retained quotes 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 |
|---|---|---|
| A10 OVHcloud a10-45 24 GB per GPU · 1 GPU per instance | Previously observed quote USD 1.00/hr per instanceUSD 1.00 /hr per GPU Browse OVHcloud Details & price history Native rate: USD 1 / hour per instance Saved pricing evidence → Pricing evidence Stale — recheck |
HourlyOn-demand
No monthly commitment
Stock not verified · France · Gravelines
Billing & region detailsHourly compute is pay-as-you-go for actual resource usage measured to the second, with no monthly commitment. Delete or shelve the instance to release compute; storage and other services remain separate. |
| A10 OVHcloud a10-90 24 GB per GPU · 2 GPUs per instance | Previously observed quote USD 2.00/hr per instanceUSD 1.00 /hr per GPU Browse OVHcloud Details & price history Native rate: USD 2 / hour per instance Saved pricing evidence → Pricing evidence Stale — recheck |
HourlyOn-demand
No monthly commitment
Stock not verified · France · Gravelines
Billing & region detailsHourly compute is pay-as-you-go for actual resource usage measured to the second, with no monthly commitment. Delete or shelve the instance to release compute; storage and other services remain separate. |
| A10 OVHcloud a10-180 24 GB per GPU · 4 GPUs per instance | Previously observed quote USD 4.00/hr per instanceUSD 1.00 /hr per GPU Browse OVHcloud Details & price history Native rate: USD 4 / hour per instance Saved pricing evidence → Pricing evidence Stale — recheck |
HourlyOn-demand
No monthly commitment
Stock not verified · France · Gravelines
Billing & region detailsHourly compute is pay-as-you-go for actual resource usage measured to the second, with no monthly commitment. Delete or shelve the instance to release compute; storage and other services remain separate. |
| A10 Lambda 1x A10 24 GB on-demand 24 GB per GPU · 1 GPU per instance | Previously observed quote USD 1.29/hr per instanceUSD 1.29 /hr per GPU Browse Lambda Details & price history Pricing evidence Stale — recheck |
HourlyOn-demand
Minimum term unverified
Stock not verified · Location not specified
Billing & region detailsHourly on-demand; minimum commitment unverified. |
| A10 Lambda 1x A10 on-demand 24 GB per GPU · 1 GPU per instance | Previously observed quote USD 1.29/hr per instanceUSD 1.29 /hr per GPU Browse Lambda Details & price history Pricing evidence Stale — recheck |
HourlyOn-demand
No monthly commitment
Stock not verified · Location not specified
Billing & region detailsOn-demand usage; no monthly reservation. |
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. | |||||||