The L40 is newer, with 2x the memory and 13% more bandwidth.
At a glance
Memory
2x more on L40
- A5000
- 24 GB
- L40
- 48 GB
Memory bandwidth
13% higher on L40
- A5000
- 768 GB/s
- L40
- 864 GB/s
Cheapest on-demand
49% cheaper on A5000
- A5000
- $0.23 /GPU/hr
- L40
- $0.46 /GPU/hr
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | A5000 | L40 | Difference |
|---|---|---|---|
| On-demand | $1.24 /GPU/hr from $0.23 | $1.05 /GPU/hr from $0.46 | 15% cheaper on L40 |
| Reserved | $0.35 /GPU/hr from $0.23 (1 mo) | -- /GPU/hr from $0.70 | |
| Spot | -- /GPU/hr from $0.09 | $0.78 /GPU/hr from $0.40 |
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 spot on the A5000 and reserved on the L40: 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
A5000 vs L40 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | A5000 | L40 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 24 GB GDDR6 | 48 GB GDDR6 | 2x more on L40 |
| Bandwidth | 768 GB/s | 864 GB/s | 13% higher on L40 |
| Bus width | 384-bit | 384-bit | Identical |
| Compute · dense | |||
| FP8 | Not supported | 362 TFLOPS | L40 only |
| FP16 / BF16 | 111.1 TFLOPS | 181.1 TFLOPS | 63% higher on L40 |
| INT8 | 362 TOPS | ||
| FP32 | 27.8 TFLOPS | 90.5 TFLOPS | 3.3x higher on L40 |
| Platform | |||
| Interconnect | NVLink 112 GB/s | PCIe only | NVLink on A5000 only |
| Board power | 230 W | 300 W | 30% higher on L40 |
| Released | Q2 2021 | Q4 2022 | 2 years newer on L40 |
| Precision | |||
| Supported formats | FP16BF16TF32FP32INT4INT8 | FP8FP16BF16TF32FP32INT4INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: A5000 datasheet and L40 datasheet.
Where to rent them
Providers that rent these GPUs, with each one's cheapest rate. Providers that rent both are listed first.
| Provider | A5000 | L40 |
|---|---|---|
Vast.ai
USA
|
$0.23 /GPU/hr On-demand | $0.46 /GPU/hr On-demand |
GPU.ai
UAE
|
$0.24 /GPU/hr On-demand | $0.78 /GPU/hr On-demand |
Sesterce
France
|
$1.56 /GPU/hr On-demand | $0.97 /GPU/hr On-demand |
Salad
Distributed
|
$0.25 /GPU/hr On-demand | -- |
Runcrate
USA
|
$1.85 /GPU/hr On-demand PCIe | -- |
Exoscale
Switzerland
|
$1.14 /GPU/hr On-demand | -- |
Paperspace
USA
|
$1.38 /GPU/hr On-demand | -- |
Database Mart
USA
|
$0.25 /GPU/hr Reserved | -- |
Runpod
USA
|
-- | $0.69 /GPU/hr On-demand |
Thunder Compute
USA
|
-- | $0.79 /GPU/hr On-demand |
Massed Compute
USA
|
-- | $0.86 /GPU/hr On-demand |
Hyperstack
UK
|
-- | $1.00 /GPU/hr On-demand |
Oblivus
USA
|
-- | $1.05 /GPU/hr On-demand PCIe |
12 providers list the A5000 and 13 the L40. Every listing is on the A5000 page and the L40 page.
Similar GPUs
Other comparisons in the same class.
-
Nvidia RTX 6000 Ada
48 GB GDDR6 · 25% more bandwidth than the A5000
From $0.49 /GPU/hr Compare -
Nvidia A40
48 GB GDDR6 · PCIe only
From $0.40 /GPU/hr Compare
-
Nvidia A4000
16 GB GDDR6 · 42% less bandwidth than the A5000
From $0.07 /GPU/hr Compare
-
Nvidia A100
80 GB HBM2e · 2.2x the bandwidth of the L40
From $0.40 /GPU/hr Compare
-
Nvidia L40S
48 GB GDDR6 · released Q3 2023
From $0.38 /GPU/hr Compare
Our data for Nvidia A5000 was last updated on Sept. 14, 2026, and for Nvidia L40 on Sept. 14, 2026.