Two Nvidia consumer GPUs on the Blackwell architecture: 16 GB GDDR7 against 32 GB GDDR7 and 87% more memory bandwidth on the RTX 5090.
At a glance
Updated 8 minutes ago- Memory
- 16 GB
- GDDR7
- Memory bandwidth
- 960 GB/s
- From
- $0.12 /GPU/hr
- 5 providers
- Memory
- 32 GB
- GDDR7
- Memory bandwidth
- 1.79 TB/s
- From
- $0.35 /GPU/hr
- 20 providers
Price comparison
Cheapest listed price per GPU per hour by billing type, and the median across providers.
| Billing | RTX 5080 | RTX 5090 | Difference |
|---|---|---|---|
| On-demand | $0.12 | $0.35 | 3x more expensive on RTX 5090 |
| Spot | $0.17 | $0.25 | 31% cheaper on RTX 5080 |
| Reserved | No reserved listings | $0.21 | |
| Median | $0.36 | $0.69 | 47% cheaper on RTX 5080 |
Median: Median across providers, one vote each, so a large catalog does not outweigh a small one.
Price history
RTX 5080 vs RTX 5090 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | RTX 5080 | RTX 5090 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 16 GB GDDR7 | 32 GB GDDR7 | 2x more on RTX 5090 |
| Bandwidth | 960 GB/s | 1,792 GB/s | 1.9x higher on RTX 5090 |
| Bus width | 256-bit | 512-bit | 2x wider on RTX 5090 |
| Compute · dense | |||
| FP4 | 900.4 TFLOPS | 1,676 TFLOPS | 1.9x higher on RTX 5090 |
| FP8 | 225.1 TFLOPS | 419 TFLOPS | 1.9x higher on RTX 5090 |
| FP16 / BF16 | 112.6 TFLOPS | 209.5 TFLOPS | 1.9x higher on RTX 5090 |
| INT8 | 450.2 TOPS | 838 TOPS | 1.9x higher on RTX 5090 |
| FP32 | 56.3 TFLOPS | 104.8 TFLOPS | 1.9x higher on RTX 5090 |
| Platform | |||
| Interconnect | PCIe only | PCIe only | |
| Board power | 360 W | 575 W | 1.6x higher on RTX 5090 |
| Released | Q1 2025 | Q1 2025 | |
| Precision | |||
| Supported formats | FP4FP8FP16BF16TF32FP32INT8 | FP4FP8FP16BF16TF32FP32INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: RTX 5080 datasheet and RTX 5090 datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | RTX 5080 /GPU/hr | RTX 5090 /GPU/hr |
|---|---|---|
Theta EdgeCloud
|
On-Demand $0.12 | On-Demand $0.82 |
Salad
|
On-Demand $0.42 | On-Demand $0.45 |
Vast.ai
|
On-Demand $1.79 | On-Demand $10.67 |
SwissGPU
|
On-Demand $0.31 | -- |
Runpod
|
On-Demand $0.39 | -- |
HyperAI
|
-- | On-Demand $0.35 |
GPUhub
|
-- | On-Demand $0.46 |
Nova Cloud
|
-- | On-Demand $0.63 |
Lium
|
-- | On-Demand $0.69 |
GPU.ai
|
-- | On-Demand $53.34 |
5 providers list the RTX 5080 and 20 the RTX 5090. Every listing is on the RTX 5080 page and the RTX 5090 page.
Similar GPUs
Other comparisons in the same class.
Our data for Nvidia RTX 5080 was last updated on Sept. 7, 2026, and for Nvidia RTX 5090 on Sept. 7, 2026.