The L40 has 2.4x the memory and 35% more bandwidth. The A4500 is cheaper right now.
At a glance
Memory
2.4x more on L40
- A4500
- 20 GB
- L40
- 48 GB
Memory bandwidth
35% higher on L40
- A4500
- 640 GB/s
- L40
- 864 GB/s
Cheapest on-demand
77% cheaper on A4500
- A4500
- $0.18 /GPU/hr
- L40
- $0.79 /GPU/hr
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | A4500 | L40 | Difference |
|---|---|---|---|
| On-demand | -- /GPU/hr from $0.18 | $1.06 /GPU/hr from $0.79 | |
| Reserved | On request | -- /GPU/hr from $0.70 | |
| Spot | No spot listings | $0.80 /GPU/hr from $0.78 |
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 on the A4500 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
A4500 vs L40 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | A4500 | L40 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 20 GB GDDR6 | 48 GB GDDR6 | 2.4x more on L40 |
| Bandwidth | 640 GB/s | 864 GB/s | 35% higher on L40 |
| Bus width | 320-bit | 384-bit | 20% wider on L40 |
| Compute · dense | |||
| FP8 | Not supported | 362 TFLOPS | L40 only |
| FP16 / BF16 | 94.6 TFLOPS | 181.1 TFLOPS | 91% higher on L40 |
| INT8 | 362 TOPS | ||
| FP32 | 23.7 TFLOPS | 90.5 TFLOPS | 3.8x higher on L40 |
| Platform | |||
| Interconnect | PCIe only | PCIe only | |
| Board power | 200 W | 300 W | 50% higher on L40 |
| Released | Q4 2021 | Q4 2022 | 11 months newer on L40 |
| Precision | |||
| Supported formats | FP16BF16TF32FP32INT4INT8 | FP8FP16BF16TF32FP32INT4INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: A4500 datasheet and L40 datasheet.
Where to rent them
Providers that rent these GPUs, with each one's cheapest rate. No provider we track offers both right now.
| Provider | A4500 | L40 |
|---|---|---|
Lium
Distributed
|
$0.18 /GPU/hr On-demand | -- |
Runpod
USA
|
On request Reserved | -- |
Thunder Compute
USA
|
-- | $0.79 /GPU/hr On-demand |
GPU.ai
UAE
|
-- | $0.86 /GPU/hr On-demand |
Massed Compute
USA
|
-- | $0.86 /GPU/hr On-demand |
Sesterce
France
|
-- | $0.97 /GPU/hr On-demand |
Oblivus
USA
|
-- | $1.05 /GPU/hr On-demand PCIe |
Spheron
Singapore
|
-- | $1.06 /GPU/hr On-demand PCIe |
Runcrate
USA
|
-- | $1.26 /GPU/hr On-demand PCIe |
EmpirioLabs AI
USA
|
-- | $1.50 /GPU/hr On-demand |
2 providers list the A4500 and 11 the L40. Every listing is on the A4500 page and the L40 page.
Similar GPUs
Other comparisons in the same class.
Our data for Nvidia A4500 was last updated on Sept. 14, 2026, and for Nvidia L40 on Sept. 14, 2026.