NVIDIA · Ampere
RTX 3090 Ti 24 GB rental prices and specifications
Ampere desktop GPU with 24 GB GDDR6X.
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 RTX 3090 Ti 24 GB 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
4 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 |
|---|---|---|
| RTX 3090 Ti 24 GB SaladCloud Salad Container Engine RTX 3090 Ti High priority 24 GB per GPU · 1 GPU per instance | Previously observed quote USD 0.19/hr per instanceUSD 0.19 /hr per GPU Browse SaladCloud Details & price history Native rate: USD 0.19 / hour per GPU Saved pricing evidence → Pricing evidence Stale — recheck |
HourlyOn-demand
No monthly commitment
Stock not verified · Location not specified
Billing & region detailsNo minimum commitment; prepaid credits required. Billed per second in running state; allocation, image download and cold start are free. |
Prices and availability can change. Confirm the current offer with the provider. Taxes and extra services are additional.
USD · Hourly · Spot / interruptible
| GPU / provider | Instance price / offer | Terms / location |
|---|---|---|
| RTX 3090 Ti 24 GB SaladCloud Salad Container Engine RTX 3090 Ti Medium priority 24 GB per GPU · 1 GPU per instance | Previously observed quote USD 0.16/hr per instanceUSD 0.16 /hr per GPU Browse SaladCloud Details & price history Native rate: USD 0.16 / hour per GPU Saved pricing evidence → Pricing evidence Stale — recheck |
HourlySpot / interruptible
No monthly commitment
Stock not verified · Location not specified
Billing & region detailsNo minimum commitment; prepaid credits required. Billed per second in running state; allocation, image download and cold start are free. |
| RTX 3090 Ti 24 GB SaladCloud Salad Container Engine RTX 3090 Ti Low priority 24 GB per GPU · 1 GPU per instance | Previously observed quote USD 0.13/hr per instanceUSD 0.13 /hr per GPU Browse SaladCloud Details & price history Native rate: USD 0.13 / hour per GPU Saved pricing evidence → Pricing evidence Stale — recheck |
HourlySpot / interruptible
No monthly commitment
Stock not verified · Location not specified
Billing & region detailsNo minimum commitment; prepaid credits required. Billed per second in running state; allocation, image download and cold start are free. |
| RTX 3090 Ti 24 GB SaladCloud Salad Container Engine RTX 3090 Ti Lowest priority 24 GB per GPU · 1 GPU per instance | Previously observed quote USD 0.10/hr per instanceUSD 0.10 /hr per GPU Browse SaladCloud Details & price history Native rate: USD 0.1 / hour per GPU Saved pricing evidence → Pricing evidence Stale — recheck |
HourlySpot / interruptible
No monthly commitment
Stock not verified · Location not specified
Billing & region detailsNo minimum commitment; prepaid credits required. Billed per second in running state; allocation, image download and cold start are free. |
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. | |||||||