A data center GPU against a consumer card, one Pascal and one Ampere: 24 GB GDDR5 against 8 GB GDDR6 and 29% more memory bandwidth on the RTX 3070.
At a glance
Updated 8 minutes ago- Memory
- 24 GB
- GDDR5
- Memory bandwidth
- 346 GB/s
- From
- --
- Memory
- 8 GB
- GDDR6
- Memory bandwidth
- 448 GB/s
- From
- $0.10 /GPU/hr
- 3 providers
Price comparison
Cheapest listed price per GPU per hour by billing type, and the median across providers.
| Billing | P40 | RTX 3070 | Difference |
|---|---|---|---|
| On-demand | -- | $0.10 | |
| Spot | No spot listings | $0.04 | |
| Median | -- | $0.10 |
Median: Median across providers, one vote each, so a large catalog does not outweigh a small one.
Price history
P40 vs RTX 3070 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | P40 | RTX 3070 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 24 GB GDDR5 | 8 GB GDDR6 | 3x more on P40 |
| Bandwidth | 346 GB/s | 448 GB/s | 1.3x higher on RTX 3070 |
| Bus width | 384-bit | 256-bit | 1.5x wider on P40 |
| Compute · dense | |||
| FP16 / BF16 | 40.6 TFLOPS | ||
| INT8 | 47 TOPS | 162.6 TOPS | 3.5x higher on RTX 3070 |
| FP32 | 12 TFLOPS | 20.3 TFLOPS | 1.7x higher on RTX 3070 |
| Platform | |||
| Interconnect | PCIe only | PCIe only | |
| Board power | 250 W | 220 W | 1.1x higher on P40 |
| Released | Q3 2016 | Q4 2020 | 4 years newer on RTX 3070 |
| Precision | |||
| Supported formats | FP16FP32INT8 | FP16BF16TF32FP32INT4INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: P40 datasheet and RTX 3070 datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | P40 /GPU/hr | RTX 3070 /GPU/hr |
|---|---|---|
Salad
|
-- | On-Demand $0.10 |
Theta EdgeCloud
|
-- | On-Demand $0.10 |
Runpod
|
-- | On-Demand $0.13 |
Similar GPUs
Other comparisons in the same class.
Our data for Nvidia P40 was last updated on Sept. 7, 2026, and for Nvidia RTX 3070 on Sept. 7, 2026.