A data center GPU against a consumer card on the Ada Lovelace architecture: 48 GB GDDR6 against 24 GB GDDR6X and 17% more memory bandwidth on the RTX 4090.
At a glance
Updated 5 minutes ago- Memory
- 48 GB
- GDDR6
- Memory bandwidth
- 864 GB/s
- From
- $0.33 /GPU/hr
- 14 providers
- Memory
- 24 GB
- GDDR6X
- Memory bandwidth
- 1.01 TB/s
- From
- $0.23 /GPU/hr
- 18 providers
Price comparison
Cheapest listed price per GPU per hour by billing type, and the median across providers.
| Billing | L40 | RTX 4090 | Difference |
|---|---|---|---|
| On-demand | $0.33 | $0.23 | 29% cheaper on RTX 4090 |
| Spot | $0.40 | $0.15 | 2.7x more expensive on L40 |
| Reserved | $0.70 | $0.27 | 2.6x more expensive on L40 |
| Median | $1.00 | $0.41 | 2.5x 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 4090 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | L40 | RTX 4090 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 48 GB GDDR6 | 24 GB GDDR6X | 2x more on L40 |
| Bandwidth | 864 GB/s | 1,010 GB/s | 1.2x higher on RTX 4090 |
| Bus width | 384-bit | 384-bit | Identical |
| Compute · dense | |||
| FP8 | 362 TFLOPS | 330.3 TFLOPS | 1.1x higher on L40 |
| FP16 / BF16 | 181.1 TFLOPS | 165.2 TFLOPS | 1.1x higher on L40 |
| INT8 | 362 TOPS | 660.6 TOPS | 1.8x higher on RTX 4090 |
| FP32 | 90.5 TFLOPS | 82.6 TFLOPS | 1.1x higher on L40 |
| Platform | |||
| Interconnect | PCIe only | PCIe only | |
| Board power | 300 W | 450 W | 1.5x higher on RTX 4090 |
| Released | Q4 2022 | Q4 2022 | |
| Precision | |||
| Supported formats | FP8FP16BF16TF32FP32INT4INT8 | FP8FP16BF16TF32FP32INT4INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: L40 datasheet and RTX 4090 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 4090 /GPU/hr |
|---|---|---|
Lium
|
On-Demand $0.33 | On-Demand $0.30 |
Vast.ai
|
On-Demand $0.46 | On-Demand $0.32 |
GPU.ai
|
On-Demand $0.78 | On-Demand $0.34 |
EmpirioLabs AI
|
On-Demand $0.70 | -- |
Thunder Compute
|
On-Demand $0.79 | -- |
Massed Compute
|
On-Demand $0.86 | -- |
Sesterce
|
On-Demand $0.97 | -- |
Runcrate
|
On-Demand $0.97 | -- |
Theta EdgeCloud
|
-- | On-Demand $0.23 |
Salad
|
-- | On-Demand $0.30 |
Novita
|
-- | On-Demand $0.33 |
Runpod
|
-- | On-Demand $0.34 |
Packet·ai
|
-- | On-Demand $0.39 |
14 providers list the L40 and 18 the RTX 4090. Every listing is on the L40 page and the RTX 4090 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 4090 on Sept. 7, 2026.