A data center GPU against a workstation card on the Ada Lovelace architecture: 48 GB GDDR6 against 24 GB GDDR6 and 2x the memory bandwidth on the L40.
At a glance
Updated 6 minutes ago- Memory
- 48 GB
- GDDR6
- Memory bandwidth
- 864 GB/s
- From
- $0.33 /GPU/hr
- 14 providers
- Memory
- 24 GB
- GDDR6
- Memory bandwidth
- 432 GB/s
- From
- $0.30 /GPU/hr
- 1 provider
Price comparison
Cheapest listed price per GPU per hour by billing type, and the median across providers.
| Billing | L40 | RTX 4500 Ada | Difference |
|---|---|---|---|
| On-demand | $0.33 | $0.30 | 11% cheaper on RTX 4500 Ada |
| Spot | $0.40 | $0.14 | 3x more expensive on L40 |
| Reserved | $0.70 | No reserved listings | |
| Median | $1.00 | $0.30 | 3.4x more expensive on L40 |
Median: Median across providers, one vote each, so a large catalog does not outweigh a small one.
Price history
L40 vs RTX 4500 Ada price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | L40 | RTX 4500 Ada | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 48 GB GDDR6 | 24 GB GDDR6 | 2x more on L40 |
| Bandwidth | 864 GB/s | 432 GB/s | 2x higher on L40 |
| Bus width | 384-bit | 192-bit | 2x wider on L40 |
| Compute · dense | |||
| FP8 | 362 TFLOPS | 317 TFLOPS | 1.1x higher on L40 |
| FP16 / BF16 | 181.1 TFLOPS | 158.5 TFLOPS | 1.1x higher on L40 |
| INT8 | 362 TOPS | ||
| FP32 | 90.5 TFLOPS | 39.6 TFLOPS | 2.3x higher on L40 |
| Platform | |||
| Interconnect | PCIe only | PCIe only | |
| Board power | 300 W | 210 W | 1.4x higher on L40 |
| Released | Q4 2022 | Q3 2023 | 10 months newer on RTX 4500 Ada |
| Precision | |||
| Supported formats | FP8FP16BF16TF32FP32INT4INT8 | FP8FP16BF16TF32FP32INT4INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: L40 datasheet and RTX 4500 Ada datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | L40 /GPU/hr | RTX 4500 Ada /GPU/hr |
|---|---|---|
Vast.ai
|
On-Demand $0.46 | On-Demand $0.30 |
Lium
|
On-Demand $0.33 | -- |
EmpirioLabs AI
|
On-Demand $0.70 | -- |
GPU.ai
|
On-Demand $0.78 | -- |
Thunder Compute
|
On-Demand $0.79 | -- |
Massed Compute
|
On-Demand $0.86 | -- |
Sesterce
|
On-Demand $0.97 | -- |
Runcrate
|
On-Demand $0.97 | -- |
14 providers list the L40 and 1 the RTX 4500 Ada. Every listing is on the L40 page and the RTX 4500 Ada page.
Similar GPUs
Other comparisons in the same class.
Our data for Nvidia L40 was last updated on Sept. 7, 2026, and for Nvidia RTX 4500 Ada on Sept. 7, 2026.