Two Nvidia data center GPUs, one Ada Lovelace and one Pascal: 24 GB GDDR6 against 8 GB GDDR5 and 56% more memory bandwidth on the L4.
At a glance
Updated 7 minutes agoPrice comparison
Cheapest listed price per GPU per hour by billing type, and the median across providers.
| Billing | L4 | P4 | Difference |
|---|---|---|---|
| On-demand | $0.32 | $0.65 | 2x more expensive on P4 |
| Spot | $0.23 | $0.12 | 47% cheaper on P4 |
| Reserved | $0.32 | $0.34 | 8% cheaper on L4 |
| Median | $0.90 | $0.81 | 9% cheaper on P4 |
Median: Median across providers, one vote each, so a large catalog does not outweigh a small one.
Price history
L4 vs P4 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | L4 | P4 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 24 GB GDDR6 | 8 GB GDDR5 | 3x more on L4 |
| Bandwidth | 300 GB/s | 192 GB/s | 1.6x higher on L4 |
| Bus width | 192-bit | 256-bit | 1.3x wider on P4 |
| Compute · dense | |||
| FP8 | 242 TFLOPS | Not supported | L4 only |
| FP16 / BF16 | 121 TFLOPS | ||
| INT8 | 242 TOPS | 22 TOPS | 11x higher on L4 |
| FP32 | 30.3 TFLOPS | 5.5 TFLOPS | 5.5x higher on L4 |
| Platform | |||
| Interconnect | PCIe only | PCIe only | |
| Board power | 72 W | 75 W | Within 5% |
| Released | Q1 2023 | Q3 2016 | 6 years newer on L4 |
| Precision | |||
| Supported formats | FP8FP16BF16TF32FP32INT4INT8 | FP16FP32INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: L4 datasheet and P4 datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | L4 /GPU/hr | P4 /GPU/hr |
|---|---|---|
|
|
On-Demand $0.32 | -- |
|
|
On-Demand $0.44 | -- |
|
|
On-Demand $0.49 | -- |
|
|
On-Demand $0.69 | -- |
|
|
On-Demand $0.91 | -- |
|
|
On-Demand $1.04 | -- |
|
|
On-Demand $1.05 | -- |
|
|
On-Demand $0.42 | -- |
|
|
-- | On-Demand $0.65 |
19 providers list the L4 and 1 the P4. Every listing is on the L4 page and the P4 page.
Similar GPUs
Other comparisons in the same class.
Our data for Nvidia L4 was last updated on Sept. 7, 2026, and for Nvidia P4 on Sept. 7, 2026.