The RTX 5090 is newer, with 33% more memory and 6x the bandwidth.
At a glance
Memory
33% more on RTX 5090
- L4
- 24 GB
- RTX 5090
- 32 GB
Memory bandwidth
6x higher on RTX 5090
- L4
- 300 GB/s
- RTX 5090
- 1,792 GB/s
Cheapest on-demand
8% cheaper on L4
- L4
- $0.32 /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 | L4 | RTX 5090 | Difference |
|---|---|---|---|
| On-demand | $0.89 /GPU/hr from $0.32 | $0.66 /GPU/hr from $0.35 | 25% cheaper on RTX 5090 |
| Reserved | $0.52 /GPU/hr from $0.32 (36 mo) | $0.59 /GPU/hr from $0.21 (1 mo) | 13% cheaper on L4 |
| Spot | $0.41 /GPU/hr from $0.13 | $0.47 /GPU/hr from $0.25 | 13% cheaper on L4 |
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. Verify before provisioning. More on how we price.
Price history
L4 vs RTX 5090 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | L4 | RTX 5090 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 24 GB GDDR6 | 32 GB GDDR7 | 33% more on RTX 5090 |
| Bandwidth | 300 GB/s | 1,792 GB/s | 6x higher on RTX 5090 |
| Bus width | 192-bit | 512-bit | 2.7x wider on RTX 5090 |
| Compute · dense | |||
| FP4 | Not supported | 1,676 TFLOPS | RTX 5090 only |
| FP8 | 242 TFLOPS | 419 TFLOPS | 73% higher on RTX 5090 |
| FP16 / BF16 | 121 TFLOPS | 209.5 TFLOPS | 73% higher on RTX 5090 |
| INT8 | 242 TOPS | 838 TOPS | 3.5x higher on RTX 5090 |
| FP32 | 30.3 TFLOPS | 104.8 TFLOPS | 3.5x higher on RTX 5090 |
| Platform | |||
| Interconnect | PCIe only | PCIe only | |
| Board power | 72 W | 575 W | 8x higher on RTX 5090 |
| Released | Q1 2023 | Q1 2025 | 2 years newer on RTX 5090 |
| Precision | |||
| Supported formats | FP8FP16BF16TF32FP32INT4INT8 | FP4FP8FP16BF16TF32FP32INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: L4 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 | L4 | RTX 5090 |
|---|---|---|
Vast.ai
USA
|
$0.32 /GPU/hr On-demand | $0.43 /GPU/hr On-demand |
GPU.ai
UAE
|
$0.32 /GPU/hr On-demand | $0.47 /GPU/hr On-demand |
Runpod
USA
|
$0.49 /GPU/hr On-demand | $0.69 /GPU/hr On-demand |
Runcrate
USA
|
$1.05 /GPU/hr On-demand PCIe | $0.77 /GPU/hr On-demand PCIe |
Jarvislabs
India
|
$0.44 /GPU/hr On-demand | -- |
UpCloud
Finland
|
$0.69 /GPU/hr On-demand | -- |
Scaleway
France
|
$0.90 /GPU/hr On-demand | -- |
Sesterce
France
|
$1.04 /GPU/hr On-demand | -- |
HyperAI
Hong Kong
|
-- | $0.35 /GPU/hr On-demand |
Lium
Distributed
|
-- | $0.50 /GPU/hr On-demand |
Salad
Distributed
|
-- | $0.50 /GPU/hr On-demand |
Nova Cloud
Canada
|
-- | $0.66 /GPU/hr On-demand PCIe |
21 providers list the L4 and 21 the RTX 5090. Every listing is on the L4 page and the RTX 5090 page.
Similar GPUs
Other comparisons in the same class.
-
Nvidia T4
16 GB GDDR6 · released Q3 2018
From $0.15 /GPU/hr Compare -
Nvidia A10
24 GB GDDR6 · 2x the bandwidth of the L4
From $0.24 /GPU/hr Compare
-
Nvidia L40
48 GB GDDR6 · 2.9x the bandwidth of the L4
From $0.46 /GPU/hr Compare
-
Nvidia RTX PRO 6000
96 GB GDDR7 · workstation card
From $0.66 /GPU/hr Compare
-
Nvidia RTX 4090
24 GB GDDR6X · 44% less bandwidth than the RTX 5090
From $0.33 /GPU/hr Compare
Our data for Nvidia L4 was last updated on Sept. 14, 2026, and for Nvidia RTX 5090 on Sept. 14, 2026.