Nvidia RTX 5090
Top Blackwell consumer GPU for local AI development and rendering.
Compare vs other GPUs →Key Specifications
Compare Cloud Provider Prices
For smaller projects, the RTX 5090 is available around $0.27/hr per GPU (spot instance). This tier offers a 97% discount compared to the higher end of the market ($10.37/hr).
How we sort results
Default ranking
Our algorithm weighs five factors to find the most relevant matches for you:
- Price: We blend total hourly price with price-per-GPU to balance affordability and value.
- Specs: We favor offers with higher CPU, RAM, and GPU Memory.
- Billing: We favor on-demand billing for simplicity and flexibility over spot instances, reservations, and custom quotes.
- Location: We blend both datacenter proximity and provider HQ location. Datacenter location matters for latency, while HQ location matters for compliance and support.
- Provider diversity: Each time a provider appears in the list, their subsequent offerings are ranked a little lower, so one provider's offerings don't crowd out the top positions.
Sorting and filtering
Click any column header to sort by that column. Use the filters above the table to narrow results by billing type, GPU count, vCPUs, or RAM. Custom sorting resets the default relevance ranking.
Transparency and funding
Ads and sponsors: Any paid placements are fixed at the top and clearly labeled as sponsored content.
Affiliates: Any affiliate links will be indicated to you as well. We may earn a commission if you click them, but this never influences the ranking order.
| Provider | GPUs | Total VRAM | vCPUs | RAM | Billing | $/GPU/h | Total/h | Availability | |
|---|---|---|---|---|---|---|---|---|---|
GPUhub
Our sponsor
|
1x RTX 5090 1x RTX 5090 32GB | 32GB | 32 | 100GB | On-Demand Pay-as-you-go pricing. No term commitments. | $0.48 | $0.48 | Available | View |
Runpod
|
1x RTX 5090 1x RTX 5090 32GB (community-cloud) | 32GB | 10 | 32GB | On-Demand Pay-as-you-go pricing. No term commitments. | $0.69 | $0.69 | Available | View |
Novita
|
1x RTX 5090 1x RTX 5090 32GB | 32GB | -- | -- | On-Demand Pay-as-you-go pricing. No term commitments. | $0.72 | $0.72 | Unknown | View |
Theta EdgeCloud
|
1x RTX 5090 1x RTX 5090 31GB | 31GB | 24 | 31GB | On-Demand Pay-as-you-go pricing. No term commitments. | $0.64 | $0.64 | Available | View |
|
Runpod
|
1x RTX 5090 1x RTX 5090 32GB (secure-cloud) | 32GB | 10 | 32GB | On-Demand Pay-as-you-go pricing. No term commitments. | $0.99 | $0.99 | Available | View |
Sesterce
|
1x RTX 5090 1x RTX 5090 32GB | 32GB | 12 | 120GB | On-Demand Pay-as-you-go pricing. No term commitments. | $0.71 | $0.71 | Available | View |
Nova Cloud
|
1x RTX 5090 PCIe 1x RTX 5090 32GB PCIe | 32GB | 22 | 88GB | On-Demand Pay-as-you-go pricing. No term commitments. | $0.78 | $0.78 | Available | View |
|
Novita
|
8x RTX 5090 8x RTX 5090 32GB | 256GB | -- | -- | On-Demand Pay-as-you-go pricing. No term commitments. | $0.72 | $5.76 | Unknown | View |
|
Runpod
|
2x RTX 5090 2x RTX 5090 32GB (community-cloud) | 64GB | 20 | 64GB | On-Demand Pay-as-you-go pricing. No term commitments. | $0.69 | $1.38 | Available | View |
SwissGPU
|
1x RTX 5090 1x RTX 5090 32GB (RTX 5090) | 32GB | 16 | 64GB | On-Demand Pay-as-you-go pricing. No term commitments. | $0.63 | $0.63 | Unknown | View |
|
Sesterce
|
2x RTX 5090 2x RTX 5090 32GB | 64GB | 24 | 240GB | On-Demand Pay-as-you-go pricing. No term commitments. | $0.71 | $1.43 | Available | View |
Database Mart
|
1x RTX 5090 1x RTX 5090 32GB (Advanced GPU VPS - RTX 5090) | 32GB | 32 | 84GB | Reserved (1mo) Reserved capacity with a 1-month minimum commitment. | $0.62 | $0.62 | Unknown | View |
|
Nova Cloud
|
2x RTX 5090 PCIe 2x RTX 5090 32GB PCIe | 64GB | 44 | 176GB | On-Demand Pay-as-you-go pricing. No term commitments. | $0.78 | $1.56 | Available | View |
Vast.ai
|
1x RTX 5090 1x RTX 5090 32GB (34278011) | 32GB | 384 | 64GB | On-Demand Pay-as-you-go pricing. No term commitments. | $0.80 | $0.80 | Available | View |
Salad
|
1x RTX 5090 1x RTX 5090 32GB (RTX 5090) | 32GB | 4 | 8GB | On-Demand Pay-as-you-go pricing. No term commitments. | $0.27 | $0.27 | Available | View |
|
Database Mart
|
1x RTX 5090 1x RTX 5090 32GB (Enterprise Dedicated GPU Server - RTX 5090) | 32GB | 36 | 256GB | Reserved (1mo) Reserved capacity with a 1-month minimum commitment. | $0.83 | $0.83 | Unknown | View |
|
Nova Cloud
|
4x RTX 5090 PCIe 4x RTX 5090 32GB PCIe | 128GB | 88 | 352GB | On-Demand Pay-as-you-go pricing. No term commitments. | $0.78 | $3.12 | Available | View |
|
Vast.ai
|
1x RTX 5090 1x RTX 5090 32GB (39335116) | 32GB | 384 | 128GB | On-Demand Pay-as-you-go pricing. No term commitments. | $1.07 | $1.07 | Available | View |
|
Database Mart
|
2x RTX 5090 2x RTX 5090 32GB (Enterprise Multi-GPU Dedicated Server - 2xRTX 5090) | 64GB | 44 | 256GB | Reserved (1mo) Reserved capacity with a 1-month minimum commitment. | $0.76 | $1.53 | Unknown | View |
|
Novita
|
1x RTX 5090 1x RTX 5090 32GB | 32GB | -- | -- | Spot Variable spot pricing with potential interruptions. | $0.36 | $0.36 | Unknown | View |
| No offerings matching your filters. | |||||||||
Heads up: We do our best to keep these prices accurate. However, cloud costs may fluctuate based on region, usage, and other factors not listed here. These are estimates based on common setups and are for informational purposes only. Always verify current rates with the provider before provisioning.
Frequently Asked Questions
Why choose the RTX 5090?
32GB GDDR7 with Blackwell FP4 Tensor Cores. Highest consumer GPU performance available. Strong for local AI development, LoRA fine-tuning, and image generation.
When is the RTX 5090 not a good fit?
Consumer GeForce GPU. No ECC memory. Subject to Nvidia's consumer EULA, which may restrict data center use. For production workloads, consider the L40S or RTX 6000 Ada.
Are RTX 5090 prices going up or down?
On-demand pricing has increased by about 122% since June 2025, from $0.90 to $1.99/hr per GPU.
What size AI models can the RTX 5090 run?
With 32GB of VRAM, the RTX 5090 can typically run 7B to 13B models in FP16, or larger models in 4-bit quantized form.
How much VRAM does the RTX 5090 have?
The RTX 5090 has 32GB of VRAM. Multi-GPU setups increase total memory, but that memory is not automatically pooled across GPUs.
What is the RTX 5090's memory bandwidth?
The RTX 5090 has 1,792 GB/s of memory bandwidth. Higher bandwidth helps with faster data transfer between GPU memory and compute cores.
What data types does the RTX 5090 support?
The RTX 5090 supports 7 precision formats. Training: BF16, FP16, TF32, FP32. Inference: FP4, FP8, INT8.
Does the RTX 5090 support NVLink?
No. The RTX 5090 is a PCIe-only GPU with no NVLink, so it is better suited to single-GPU inference and smaller-scale workloads than large distributed training jobs.
How much does the RTX 5090 cost per hour?
RTX 5090 pricing currently ranges from $0.27/hr to $10.37/hr per GPU, depending on the provider, instance type, and billing model.
How much does the RTX 5090 cost per month?
At 720 hours per month, one RTX 5090 can cost between $194.47 to $7,466.72 per month, depending on the provider. Reserved and spot pricing can lower that further.
Which cloud providers offer the RTX 5090?
The RTX 5090 is available from 12 cloud providers, including Runpod, Hostiko, BreezeHost. Pricing and availability vary by region and billing model.
Can I rent the RTX 5090 in the cloud?
Yes. We currently track 204 RTX 5090 listings across 12 cloud providers:
Billing type Listings Avg $/GPU/hr On-demand 84 $1.19/hr Reserved 49 $0.89/hr Spot 71 $0.79/hr
Technical Specifications
| GPU Architecture | Blackwell |
| CUDA Cores | 21760 |
| Boost Clock | 2.41 GHz |
| Base Clock | 2.01 GHz |
| Tensor Cores | 5th Generation |
| AI Performance | 3352 AI TOPS |
| RT Cores | 4th Generation |
| RT Performance | 318 TFLOPS |
| Memory Config | 32 GB GDDR7 |
| Memory Interface | 512-bit |
| PCI Express | Gen 5 |
| CUDA Capability | 12.0 |
| Dimensions (L x W) | 304 mm x 137 mm |
| Slot Size | 2-Slot |
| Max GPU Temperature | 90 C |
| Total Graphics Power (TGP) | 575 W |
| Required System Power | 1000 W |
| Power Connectors | 4x PCIe 8-pin (adapter) OR 1x 600 W PCIe Gen 5 cable |
| NVLink Support | No |
Source: official Nvidia RTX 5090 datasheet.
Alternatives to Nvidia RTX 5090
Last updated