The RTX 5090 is newer, with 33% more memory and 91% more bandwidth. The RTX 3090 is typically cheaper.
At a glance
Memory
33% more on RTX 5090
- RTX 3090
- 24 GB
- RTX 5090
- 32 GB
Memory bandwidth
91% higher on RTX 5090
- RTX 3090
- 936 GB/s
- RTX 5090
- 1,792 GB/s
Cheapest on-demand
71% cheaper on RTX 3090
- RTX 3090
- $0.10 /GPU/hr
- RTX 5090
- $0.35 /GPU/hr
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | RTX 3090 | RTX 5090 | Difference |
|---|---|---|---|
| On-demand | $0.19 /GPU/hr from $0.10 | $0.65 /GPU/hr from $0.35 | 71% cheaper on RTX 3090 |
| Reserved | -- /GPU/hr from $0.06 (1 mo) | $0.59 /GPU/hr from $0.21 (1 mo) | |
| Spot | -- /GPU/hr from $0.05 | $0.40 /GPU/hr from $0.25 |
Heads up: A provider's own page may quote a different figure, for example on tax, region or a promotion. A monthly-only plan shows a derived hourly rate. Medians are across providers, one vote each, so a large catalog does not outweigh a small one. No median for reserved and spot on the RTX 3090: we only show one when at least 3 providers list the GPU on that billing type. Verify before provisioning. More on how we price.
Price history
RTX 3090 vs RTX 5090 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | RTX 3090 | RTX 5090 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 24 GB GDDR6X | 32 GB GDDR7 | 33% more on RTX 5090 |
| Bandwidth | 936 GB/s | 1,792 GB/s | 91% higher on RTX 5090 |
| Bus width | 384-bit | 512-bit | 33% wider on RTX 5090 |
| Compute · dense | |||
| FP4 | Not supported | 1,676 TFLOPS | RTX 5090 only |
| FP8 | Not supported | 419 TFLOPS | RTX 5090 only |
| FP16 / BF16 | 71.2 TFLOPS | 209.5 TFLOPS | 2.9x higher on RTX 5090 |
| INT8 | 284.7 TOPS | 838 TOPS | 2.9x higher on RTX 5090 |
| FP32 | 35.6 TFLOPS | 104.8 TFLOPS | 2.9x higher on RTX 5090 |
| Platform | |||
| Interconnect | NVLink 112 GB/s | PCIe only | NVLink on RTX 3090 only |
| Board power | 350 W | 575 W | 64% higher on RTX 5090 |
| Released | Q3 2020 | Q1 2025 | 4 years newer on RTX 5090 |
| Precision | |||
| Supported formats | FP16BF16TF32FP32INT4INT8 | FP4FP8FP16BF16TF32FP32INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: RTX 3090 datasheet and RTX 5090 datasheet.
Where to rent them
Providers that rent these GPUs, with each one's cheapest rate. Providers that rent both are listed first.
| Provider | RTX 3090 | RTX 5090 |
|---|---|---|
HyperAI
Hong Kong
|
$0.10 /GPU/hr On-demand | $0.35 /GPU/hr On-demand |
Vast.ai
USA
|
$0.14 /GPU/hr On-demand | $0.43 /GPU/hr On-demand |
GPU.ai
UAE
|
$0.15 /GPU/hr On-demand | $0.43 /GPU/hr On-demand |
Lium
Distributed
|
$0.16 /GPU/hr On-demand | $0.75 /GPU/hr On-demand |
Salad
Distributed
|
$0.17 /GPU/hr On-demand | $0.50 /GPU/hr On-demand |
Runpod
USA
|
$0.22 /GPU/hr On-demand | $0.69 /GPU/hr On-demand |
EmpirioLabs AI
USA
|
$0.45 /GPU/hr On-demand | -- |
SwissGPU
Switzerland
|
$0.30 /GPU/hr On-demand | -- |
GPUhub
Singapore
|
-- | $0.46 /GPU/hr On-demand |
Nova Cloud
Canada
|
-- | $0.66 /GPU/hr On-demand PCIe |
9 providers list the RTX 3090 and 21 the RTX 5090. Every listing is on the RTX 3090 page and the RTX 5090 page.
Similar GPUs
Other comparisons in the same class.
-
Nvidia RTX 4090
24 GB GDDR6X · PCIe only
From $0.31 /GPU/hr Compare -
Nvidia RTX 3090 Ti
24 GB GDDR6X · PCIe only
From $0.19 /GPU/hr Compare
-
Nvidia RTX PRO 6000
96 GB GDDR7 · workstation card
From $0.65 /GPU/hr Compare
-
Nvidia L40S
48 GB GDDR6 · 52% less bandwidth than the RTX 5090
From $0.54 /GPU/hr Compare
Our data for Nvidia RTX 3090 was last updated on Sept. 14, 2026, and for Nvidia RTX 5090 on Sept. 14, 2026.