A data center GPU against a consumer card, one Ada Lovelace and one Ampere: 48 GB GDDR6 against 10 GB GDDR6X and 14% more memory bandwidth on the L40S.
At a glance
Updated 6 minutes ago- Memory
- 48 GB
- GDDR6
- Memory bandwidth
- 864 GB/s
- From
- $0.38 /GPU/hr
- 36 providers
- Memory
- 10 GB
- GDDR6X
- Memory bandwidth
- 760 GB/s
- From
- $0.11 /GPU/hr
- 5 providers
Price comparison
Cheapest listed price per GPU per hour by billing type, and the median across providers.
| Billing | L40S | RTX 3080 | Difference |
|---|---|---|---|
| On-demand | $0.38 | $0.11 | 3.3x more expensive on L40S |
| Spot | $0.47 | $0.04 | 11x more expensive on L40S |
| Reserved | $0.60 | No reserved listings | |
| Median | $1.28 | $0.16 | 8x more expensive on L40S |
Median: Median across providers, one vote each, so a large catalog does not outweigh a small one.
Price history
L40S vs RTX 3080 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | L40S | RTX 3080 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 48 GB GDDR6 | 10 GB GDDR6X | 4.8x more on L40S |
| Bandwidth | 864 GB/s | 760 GB/s | 1.1x higher on L40S |
| Bus width | 384-bit | 320-bit | 1.2x wider on L40S |
| Compute · dense | |||
| FP8 | 733 TFLOPS | Not supported | L40S only |
| FP16 / BF16 | 362.1 TFLOPS | 59.5 TFLOPS | 6.1x higher on L40S |
| INT8 | 733 TOPS | 238 TOPS | 3.1x higher on L40S |
| FP32 | 91.6 TFLOPS | 29.8 TFLOPS | 3.1x higher on L40S |
| Platform | |||
| Interconnect | PCIe only | PCIe only | |
| Board power | 350 W | 320 W | 1.1x higher on L40S |
| Released | Q3 2023 | Q3 2020 | 3 years newer on L40S |
| Precision | |||
| Supported formats | FP8FP16BF16TF32FP32INT4INT8 | FP16BF16TF32FP32INT4INT8 | |
Figures are for each model's headline configuration. Where a form factor carries a different number, it is named under the figure.
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: L40S datasheet and RTX 3080 datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | L40S /GPU/hr | RTX 3080 /GPU/hr |
|---|---|---|
Vast.ai
|
On-Demand $0.74 | On-Demand $0.11 |
GPU.ai
|
On-Demand $0.80 | On-Demand $0.14 |
Lium
|
On-Demand $0.38 | -- |
Novita
|
On-Demand $0.55 | -- |
EmpirioLabs AI
|
On-Demand $0.80 | -- |
Packet·ai
|
On-Demand $0.92 | -- |
Sesterce
|
On-Demand $0.97 | -- |
Massed Compute
|
On-Demand $0.97 | -- |
Salad
|
-- | On-Demand $0.18 |
Theta EdgeCloud
|
-- | On-Demand $0.21 |
Runpod
|
-- | On-Demand $0.17 |
36 providers list the L40S and 5 the RTX 3080. Every listing is on the L40S page and the RTX 3080 page.
Similar GPUs
Other comparisons in the same class.
Our data for Nvidia L40S was last updated on Sept. 7, 2026, and for Nvidia RTX 3080 on Sept. 7, 2026.