Two Nvidia data center GPUs, one Ampere and one Ada Lovelace: 24 GB GDDR6 against 48 GB GDDR6 and 44% more memory bandwidth on the L40S.
At a glance
Memory
- A10G
- 24 GB
- L40S
- 48 GB
2x more on L40S
Memory bandwidth
- A10G
- 600 GB/s
- L40S
- 864 GB/s
1.4x higher on L40S
Cheapest on-demand
- A10G
- $1.00 /GPU/hr
- L40S
- $0.55 /GPU/hr
45% cheaper on L40S
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | A10G | L40S | Difference |
|---|---|---|---|
| On-demand | -- /GPU/hr from $1.00 | $1.64 /GPU/hr from $0.55 | |
| Reserved | -- /GPU/hr from $0.43 (36 mo) | $1.11 /GPU/hr from $0.60 (12 mo) | |
| Spot | No spot listings | $1.11 /GPU/hr from $0.74 |
Heads up: A provider's own page may quote a different figure, for example on tax, region or a promotion. A monthly-only plan shows a derived hourly rate. Medians are across providers, one vote each, so a large catalog does not outweigh a small one. No median for on-demand and reserved on the A10G: we only show one when at least 3 providers list the GPU on that billing type. Verify before provisioning. More on how we price.
Price history
A10G vs L40S price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | A10G | L40S | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 24 GB GDDR6 | 48 GB GDDR6 | 2x more on L40S |
| Bandwidth | 600 GB/s | 864 GB/s | 1.4x higher on L40S |
| Bus width | 384-bit | ||
| Compute · dense | |||
| FP8 | Not supported | 733 TFLOPS | L40S only |
| FP16 / BF16 | 70 TFLOPS | 362.1 TFLOPS | 5.2x higher on L40S |
| INT8 | 140 TOPS | 733 TOPS | 5.2x higher on L40S |
| FP32 | 35 TFLOPS | 91.6 TFLOPS | 2.6x higher on L40S |
| Platform | |||
| Interconnect | PCIe only | PCIe only | |
| Board power | 300 W | 350 W | 1.2x higher on L40S |
| Released | Q2 2021 | Q3 2023 | 2 years newer on L40S |
| Precision | |||
| Supported formats | FP16BF16TF32FP32INT4INT8 | FP8FP16BF16TF32FP32INT4INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: A10G datasheet and L40S datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | A10G /GPU/hr | L40S /GPU/hr |
|---|---|---|
Hugging Face
|
On-Demand $1.00 | -- |
AWS
|
On-Demand $1.01 | -- |
Novita
|
-- | On-Demand $0.55 |
GPU.ai
|
-- | On-Demand $0.80 |
Packet·ai
|
-- | On-Demand $0.92 |
Sesterce
|
-- | On-Demand $0.97 |
Massed Compute
|
-- | On-Demand $0.97 |
Runcrate
|
-- | On-Demand $0.97 |
UpCloud
|
-- | On-Demand $1.19 |
Lyceum
|
-- | On-Demand $1.19 |
2 providers list the A10G and 34 the L40S. Every listing is on the A10G page and the L40S page.
Similar GPUs
Other comparisons in the same class.
Our data for Nvidia A10G was last updated on Sept. 7, 2026, and for Nvidia L40S on Sept. 7, 2026.