A data center GPU against a workstation card, one Ada Lovelace and one Turing: 24 GB GDDR6 against 16 GB GDDR6, 49% more memory bandwidth on the RTX 5000, and NVLink 50 GB/s on the RTX 5000 where the L4 is PCIe only.
At a glance
Memory
- L4
- 24 GB
- RTX 5000
- 16 GB
1.5x more on L4
Memory bandwidth
- L4
- 300 GB/s
- RTX 5000
- 448 GB/s
1.5x higher on RTX 5000
Cheapest on-demand
- L4
- $0.44 /GPU/hr
- RTX 5000
- $0.60 /GPU/hr
27% cheaper on L4
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | L4 | RTX 5000 | Difference |
|---|---|---|---|
| On-demand | $0.90 /GPU/hr from $0.44 | -- /GPU/hr from $0.60 | |
| Reserved | $0.53 /GPU/hr from $0.32 (36 mo) | No reserved listings | |
| Spot | -- /GPU/hr from $0.34 | No spot listings |
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 spot on the L4 and on-demand on the RTX 5000: 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
L4 vs RTX 5000 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | L4 | RTX 5000 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 24 GB GDDR6 | 16 GB GDDR6 | 1.5x more on L4 |
| Bandwidth | 300 GB/s | 448 GB/s | 1.5x higher on RTX 5000 |
| Bus width | 192-bit | 256-bit | 1.3x wider on RTX 5000 |
| Compute · dense | |||
| FP8 | 242 TFLOPS | Not supported | L4 only |
| FP16 / BF16 | 121 TFLOPS | 89.2 TFLOPS | 1.4x higher on L4 |
| INT8 | 242 TOPS | 178.4 TOPS | 1.4x higher on L4 |
| FP32 | 30.3 TFLOPS | 11.2 TFLOPS | 2.7x higher on L4 |
| Platform | |||
| Interconnect | PCIe only | NVLink 50 GB/s | NVLink on RTX 5000 only |
| Board power | 72 W | 265 W | 3.7x higher on RTX 5000 |
| Released | Q1 2023 | Q3 2018 | 5 years newer on L4 |
| Precision | |||
| Supported formats | FP8FP16BF16TF32FP32INT4INT8 | FP16FP32INT4INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: L4 datasheet and RTX 5000 datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | L4 /GPU/hr | RTX 5000 /GPU/hr |
|---|---|---|
GPU.ai
|
On-Demand $0.44 | -- |
Runpod
|
On-Demand $0.49 | -- |
UpCloud
|
On-Demand $0.69 | -- |
Scaleway
|
On-Demand $0.91 | -- |
Sesterce
|
On-Demand $1.04 | -- |
Runcrate
|
On-Demand $1.05 | -- |
Hexabyte
|
On-Demand $0.42 | -- |
Koyeb
|
On-Demand $0.70 | -- |
OVH
|
-- | On-Demand $0.60 |
Paperspace
|
-- | On-Demand $0.82 |
18 providers list the L4 and 2 the RTX 5000. Every listing is on the L4 page and the RTX 5000 page.
Similar GPUs
Other comparisons in the same class.
Our data for Nvidia L4 was last updated on Sept. 7, 2026, and for Nvidia RTX 5000 on Sept. 7, 2026.