A data center GPU against a consumer card, one Ada Lovelace and one Blackwell: 24 GB GDDR6 against 16 GB GDDR7 and 3.2x the memory bandwidth on the RTX 5080.
At a glance
Updated 8 minutes ago- Memory
- 24 GB
- GDDR6
- Memory bandwidth
- 300 GB/s
- From
- $0.44 /GPU/hr
- 18 providers
- Memory
- 16 GB
- GDDR7
- Memory bandwidth
- 960 GB/s
- From
- $0.12 /GPU/hr
- 4 providers
Price comparison
Cheapest listed price per GPU per hour by billing type, and the median across providers.
| Billing | L4 | RTX 5080 | Difference |
|---|---|---|---|
| On-demand | $0.44 | $0.12 | 3.8x more expensive on L4 |
| Spot | $0.34 | $0.18 | 47% cheaper on RTX 5080 |
| Reserved | $0.32 | No reserved listings | |
| Median | $0.91 | $0.31 | 2.9x more expensive on L4 |
Median: Median across providers, one vote each, so a large catalog does not outweigh a small one.
Price history
L4 vs RTX 5080 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | L4 | RTX 5080 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 24 GB GDDR6 | 16 GB GDDR7 | 1.5x more on L4 |
| Bandwidth | 300 GB/s | 960 GB/s | 3.2x higher on RTX 5080 |
| Bus width | 192-bit | 256-bit | 1.3x wider on RTX 5080 |
| Compute · dense | |||
| FP4 | Not supported | 900.4 TFLOPS | RTX 5080 only |
| FP8 | 242 TFLOPS | 225.1 TFLOPS | 1.1x higher on L4 |
| FP16 / BF16 | 121 TFLOPS | 112.6 TFLOPS | 1.1x higher on L4 |
| INT8 | 242 TOPS | 450.2 TOPS | 1.9x higher on RTX 5080 |
| FP32 | 30.3 TFLOPS | 56.3 TFLOPS | 1.9x higher on RTX 5080 |
| Platform | |||
| Interconnect | PCIe only | PCIe only | |
| Board power | 72 W | 360 W | 5x higher on RTX 5080 |
| Released | Q1 2023 | Q1 2025 | 2 years newer on RTX 5080 |
| Precision | |||
| Supported formats | FP8FP16BF16TF32FP32INT4INT8 | FP4FP8FP16BF16TF32FP32INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: L4 datasheet and RTX 5080 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 5080 /GPU/hr |
|---|---|---|
GPU.ai
|
On-Demand $0.44 | -- |
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 | -- |
Leaseweb
|
On-Demand $0.45 | -- |
Theta EdgeCloud
|
-- | On-Demand $0.12 |
Salad
|
-- | On-Demand $0.42 |
SwissGPU
|
-- | On-Demand $0.31 |
Runpod
|
-- | On-Demand $0.39 |
18 providers list the L4 and 4 the RTX 5080. Every listing is on the L4 page and the RTX 5080 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 5080 on Sept. 7, 2026.