The L40 has 50% more memory, while the RTX 5090 is newer and has 2.1x the bandwidth. The RTX 5090 is typically cheaper.
At a glance
Memory
50% more on L40
- L40
- 48 GB
- RTX 5090
- 32 GB
Memory bandwidth
2.1x higher on RTX 5090
- L40
- 864 GB/s
- RTX 5090
- 1,792 GB/s
Cheapest on-demand
23% cheaper on RTX 5090
- L40
- $0.46 /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 | L40 | RTX 5090 | Difference |
|---|---|---|---|
| On-demand | $1.05 /GPU/hr from $0.46 | $0.65 /GPU/hr from $0.35 | 38% cheaper on RTX 5090 |
| Reserved | -- /GPU/hr from $0.70 | $0.59 /GPU/hr from $0.21 (1 mo) | |
| Spot | $0.78 /GPU/hr from $0.40 | $0.49 /GPU/hr from $0.18 | 38% cheaper on RTX 5090 |
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 on the L40: 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
L40 vs RTX 5090 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | L40 | RTX 5090 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 48 GB GDDR6 | 32 GB GDDR7 | 50% more on L40 |
| Bandwidth | 864 GB/s | 1,792 GB/s | 2.1x 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 | 362 TFLOPS | 419 TFLOPS | 16% higher on RTX 5090 |
| FP16 / BF16 | 181.1 TFLOPS | 209.5 TFLOPS | 16% higher on RTX 5090 |
| INT8 | 362 TOPS | 838 TOPS | 2.3x higher on RTX 5090 |
| FP32 | 90.5 TFLOPS | 104.8 TFLOPS | 16% higher on RTX 5090 |
| Platform | |||
| Interconnect | PCIe only | PCIe only | |
| Board power | 300 W | 575 W | 92% higher on RTX 5090 |
| Released | Q4 2022 | 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: L40 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 | L40 | RTX 5090 |
|---|---|---|
Vast.ai
USA
|
$0.46 /GPU/hr On-demand | $0.43 /GPU/hr On-demand |
GPU.ai
UAE
|
$0.78 /GPU/hr On-demand | $0.41 /GPU/hr On-demand |
Runpod
USA
|
$0.69 /GPU/hr On-demand | -- |
Thunder Compute
USA
|
$0.79 /GPU/hr On-demand | -- |
Massed Compute
USA
|
$0.86 /GPU/hr On-demand | -- |
Sesterce
France
|
$0.97 /GPU/hr On-demand | -- |
Hyperstack
UK
|
$1.00 /GPU/hr On-demand | -- |
Oblivus
USA
|
$1.05 /GPU/hr On-demand PCIe | -- |
HyperAI
Hong Kong
|
-- | $0.35 /GPU/hr On-demand |
GPUhub
Singapore
|
-- | $0.46 /GPU/hr On-demand |
Salad
Distributed
|
-- | $0.50 /GPU/hr On-demand |
Lium
Distributed
|
-- | $0.55 /GPU/hr On-demand |
Theta EdgeCloud
Distributed
|
-- | $0.64 /GPU/hr On-demand |
Nova Cloud
Canada
|
-- | $0.66 /GPU/hr On-demand PCIe |
13 providers list the L40 and 22 the RTX 5090. Every listing is on the L40 page and the RTX 5090 page.
Similar GPUs
Other comparisons in the same class.
-
Nvidia A100
80 GB HBM2e · 2.2x the bandwidth of the L40
From $0.34 /GPU/hr Compare -
Nvidia L40S
48 GB GDDR6 · released Q3 2023
From $0.38 /GPU/hr Compare
-
Nvidia A40
48 GB GDDR6 · 19% less bandwidth than the L40
From $0.34 /GPU/hr Compare
-
Nvidia RTX PRO 6000
96 GB GDDR7 · workstation card
From $0.65 /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 L40 was last updated on Sept. 14, 2026, and for Nvidia RTX 5090 on Sept. 14, 2026.