A data center GPU against a consumer card, one Ada Lovelace and one Blackwell: 48 GB GDDR6 against 12 GB GDDR7 and 29% more memory bandwidth on the L40S.
At a glance
Updated 7 minutes ago- Memory
- 48 GB
- GDDR6
- Memory bandwidth
- 864 GB/s
- From
- $0.55 /GPU/hr
- 33 providers
- Memory
- 12 GB
- GDDR7
- Memory bandwidth
- 672 GB/s
- From
- $0.24 /GPU/hr
- 2 providers
Price comparison
Cheapest listed price per GPU per hour by billing type, and the median across providers.
| Billing | L40S | RTX 5070 | Difference |
|---|---|---|---|
| On-demand | $0.55 | $0.24 | 2.3x more expensive on L40S |
| Spot | $0.74 | $0.08 | 9.2x more expensive on L40S |
| Reserved | $0.60 | No reserved listings | |
| Median | $1.66 | $0.27 | 6.2x 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 5070 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | L40S | RTX 5070 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 48 GB GDDR6 | 12 GB GDDR7 | 4x more on L40S |
| Bandwidth | 864 GB/s | 672 GB/s | 1.3x higher on L40S |
| Bus width | 384-bit | 192-bit | 2x wider on L40S |
| Compute · dense | |||
| FP4 | Not supported | 493.9 TFLOPS | RTX 5070 only |
| FP8 | 733 TFLOPS | 123.5 TFLOPS | 5.9x higher on L40S |
| FP16 / BF16 | 362.1 TFLOPS | 61.7 TFLOPS | 5.9x higher on L40S |
| INT8 | 733 TOPS | 246.9 TOPS | 3x higher on L40S |
| FP32 | 91.6 TFLOPS | 30.9 TFLOPS | 3x higher on L40S |
| Platform | |||
| Interconnect | PCIe only | PCIe only | |
| Board power | 350 W | 250 W | 1.4x higher on L40S |
| Released | Q3 2023 | Q1 2025 | 2 years newer on RTX 5070 |
| Precision | |||
| Supported formats | FP8FP16BF16TF32FP32INT4INT8 | FP4FP8FP16BF16TF32FP32INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: L40S datasheet and RTX 5070 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 5070 /GPU/hr |
|---|---|---|
Novita
|
On-Demand $0.55 | -- |
Packet·ai
|
On-Demand $0.92 | -- |
Runcrate
|
On-Demand $0.97 | -- |
Runpod
|
On-Demand $1.09 | -- |
UpCloud
|
On-Demand $1.19 | -- |
Koyeb
|
On-Demand $1.20 | -- |
Crusoe
|
On-Demand $1.50 | -- |
Scaleway
|
On-Demand $1.70 | -- |
Salad
|
-- | On-Demand $0.24 |
Theta EdgeCloud
|
-- | On-Demand $0.26 |
33 providers list the L40S and 2 the RTX 5070. Every listing is on the L40S page and the RTX 5070 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 5070 on Sept. 7, 2026.