Two Nvidia data center GPUs on the Pascal architecture: 16 GB HBM2 against 24 GB GDDR5, 2.1x the memory bandwidth on the P100, and NVLink 160 GB/s on the P100 where the P40 is PCIe only.
At a glance
Memory
- P100
- 16 GB
- P40
- 24 GB
1.5x more on P40
Memory bandwidth
- P100
- 732 GB/s
- P40
- 346 GB/s
2.1x higher on P100
Cheapest on-demand
- P100
- $0.09 /GPU/hr
- P40
- $0.11 /GPU/hr
12% cheaper on P100
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | P100 | P40 | Difference |
|---|---|---|---|
| On-demand | $1.41 /GPU/hr from $0.09 | -- /GPU/hr from $0.11 | |
| Reserved | $1.04 /GPU/hr from $0.12 (24 mo) | No reserved listings | |
| Spot | -- /GPU/hr from $0.08 | -- /GPU/hr from $0.07 |
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 P100 and on-demand and spot on the P40: 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
P100 vs P40 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | P100 | P40 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 16 GB HBM2 | 24 GB GDDR5 | 1.5x more on P40 |
| Bandwidth | 732 GB/s | 346 GB/s | 2.1x higher on P100 |
| Bus width | 4,096-bit | 384-bit | 11x wider on P100 |
| Compute · dense | |||
| FP16 / BF16 | 18.7 TFLOPS | ||
| INT8 | Not supported | 47 TOPS | P40 only |
| FP32 | 9.3 TFLOPS | 12 TFLOPS | 1.3x higher on P40 |
| FP64 | 4.7 TFLOPS | Not supported | P100 only |
| Platform | |||
| Interconnect | NVLink 160 GB/s | PCIe only | NVLink on P100 only |
| Board power | 250 W | 250 W | Identical |
| Released | Q2 2016 | Q3 2016 | |
| Precision | |||
| Supported formats | FP16FP32FP64 | FP16FP32INT8 | |
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: P100 datasheet and P40 datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | P100 /GPU/hr | P40 /GPU/hr |
|---|---|---|
Vast.ai
|
On-Demand $0.09 | On-Demand $0.11 |
Scaleway
|
On-Demand $1.41 | -- |
Oracle Cloud
|
On-Demand $1.27 | -- |
Google Cloud
|
On-Demand $1.51 | -- |
Alibaba Cloud
|
On-Demand $1.55 | -- |
Database Mart
|
Reserved (24mo) $0.12 | -- |
Similar GPUs
Other comparisons in the same class.
-
Nvidia A100
80 GB HBM2e · 2.6x the bandwidth of the P100
From $0.40 /GPU/hr Compare -
Nvidia V100
32 GB HBM2 · 23% more bandwidth than the P100
From $0.07 /GPU/hr Compare
-
Nvidia T4
16 GB GDDR6 · 59% less bandwidth than the P100
From $0.07 /GPU/hr Compare
-
Nvidia L4
24 GB GDDR6 · 13% less bandwidth than the P40
From $0.33 /GPU/hr Compare
Our data for Nvidia P100 was last updated on Sept. 14, 2026, and for Nvidia P40 on Sept. 14, 2026.