A workstation GPU against a data center card, one Ampere and one Ada Lovelace: both with 48 GB GDDR6, 13% more memory bandwidth on the L40, and NVLink 112 GB/s on the RTX A6000 where the L40 is PCIe only.
At a glance
Updated 8 minutes ago- Memory
- 48 GB
- GDDR6
- Memory bandwidth
- 768 GB/s
- From
- $0.35 /GPU/hr
- 19 providers
- Memory
- 48 GB
- GDDR6
- Memory bandwidth
- 864 GB/s
- From
- $0.78 /GPU/hr
- 12 providers
Price comparison
Cheapest listed price per GPU per hour by billing type, and the median across providers.
| Billing | RTX A6000 | L40 | Difference |
|---|---|---|---|
| On-demand | $0.35 | $0.78 | 2.2x more expensive on L40 |
| Spot | $0.40 | $0.78 | 49% cheaper on RTX A6000 |
| Reserved | $0.35 | $0.70 | 2x more expensive on L40 |
| Median | $0.56 | $1.05 | 46% cheaper on RTX A6000 |
Median: Median across providers, one vote each, so a large catalog does not outweigh a small one.
Price history
RTX A6000 vs L40 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | RTX A6000 | L40 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 48 GB GDDR6 | 48 GB GDDR6 | Identical |
| Bandwidth | 768 GB/s | 864 GB/s | 1.1x higher on L40 |
| Bus width | 384-bit | 384-bit | Identical |
| Compute · dense | |||
| FP8 | Not supported | 362 TFLOPS | L40 only |
| FP16 / BF16 | 154.8 TFLOPS | 181.1 TFLOPS | 1.2x higher on L40 |
| INT8 | 309.7 TOPS | 362 TOPS | 1.2x higher on L40 |
| FP32 | 38.7 TFLOPS | 90.5 TFLOPS | 2.3x higher on L40 |
| Platform | |||
| Interconnect | NVLink 112 GB/s | PCIe only | NVLink on RTX A6000 only |
| Board power | 300 W | 300 W | Identical |
| Released | Q4 2020 | Q4 2022 | 2 years newer on L40 |
| Precision | |||
| Supported formats | FP16BF16TF32FP32INT4INT8 | FP8FP16BF16TF32FP32INT4INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: RTX A6000 datasheet and L40 datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | RTX A6000 /GPU/hr | L40 /GPU/hr |
|---|---|---|
Thunder Compute
|
On-Demand $0.35 | On-Demand $0.79 |
GPU.ai
|
On-Demand $0.40 | On-Demand $0.78 |
Spheron
|
On-Demand $0.54 | On-Demand $1.06 |
Massed Compute
|
On-Demand $0.55 | On-Demand $0.86 |
Runcrate
|
On-Demand $0.55 | On-Demand $0.97 |
Oblivus
|
On-Demand $0.55 | On-Demand $1.05 |
Sesterce
|
On-Demand $0.55 | On-Demand $1.10 |
Koyeb
|
On-Demand $0.75 | -- |
EmpirioLabs AI
|
-- | On-Demand $1.50 |
19 providers list the RTX A6000 and 12 the L40. Every listing is on the RTX A6000 page and the L40 page.
Similar GPUs
Other comparisons in the same class.
Our data for Nvidia RTX A6000 was last updated on Sept. 7, 2026, and for Nvidia L40 on Sept. 7, 2026.