Two Nvidia data center GPUs, one Pascal and one Volta: 24 GB GDDR5 against 32 GB HBM2, 2.6x the memory bandwidth on the V100, and NVLink 300 GB/s on the V100 where the P40 is PCIe only.
At a glance
Updated 6 minutes ago- Memory
- 24 GB
- GDDR5
- Memory bandwidth
- 346 GB/s
- From
- --
- Memory
- 32 GB
- HBM2
- Memory bandwidth
- 900 GB/s
- From
- $0.11 /GPU/hr
- 20 providers
Price comparison
Cheapest listed price per GPU per hour by billing type, and the median across providers.
| Billing | P40 | V100 | Difference |
|---|---|---|---|
| On-demand | -- | $0.11 | |
| Spot | No spot listings | $0.09 | |
| Reserved | No reserved listings | $0.13 | |
| Median | -- | $0.99 |
Median: Median across providers, one vote each, so a large catalog does not outweigh a small one.
Price history
P40 vs V100 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | P40 | V100 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 24 GB GDDR5 | 32 GB HBM2 | 1.3x more on V100 |
| Bandwidth | 346 GB/s | 900 GB/s | 2.6x higher on V100 |
| Bus width | 384-bit | 4,096-bit | 11x wider on V100 |
| Compute · dense | |||
| FP16 / BF16 | 125 TFLOPS | ||
| INT8 | 47 TOPS | ||
| FP32 | 12 TFLOPS | 15.7 TFLOPS | 1.3x higher on V100 |
| FP64 | Not supported | 7.8 TFLOPS | V100 only |
| Platform | |||
| Interconnect | PCIe only | NVLink 300 GB/s | NVLink on V100 only |
| Board power | 250 W | 300 W | 1.2x higher on V100 |
| Released | Q3 2016 | Q2 2017 | 9 months newer on V100 |
| Precision | |||
| Supported formats | FP16FP32INT8 | FP16FP32FP64INT8 | |
Figures are for each model's headline configuration. Where a form factor carries a different number, it is named under the figure.
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: P40 datasheet and V100 datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | P40 /GPU/hr | V100 /GPU/hr |
|---|---|---|
Vast.ai
|
-- | On-Demand $0.11 |
HyperAI
|
-- | On-Demand $0.14 |
Verda
|
-- | On-Demand $0.17 |
Runcrate
|
-- | On-Demand $2.57 |
Sesterce
|
-- | On-Demand $2.57 |
Geodd
|
-- | On-Demand $0.16 |
TensorDock
|
-- | On-Demand $0.28 |
Cyfuture AI
|
-- | On-Demand $0.55 |
0 providers list the P40 and 20 the V100. Every listing is on the P40 page and the V100 page.
Similar GPUs
Other comparisons in the same class.
Our data for Nvidia P40 was last updated on Sept. 7, 2026, and for Nvidia V100 on Sept. 7, 2026.