A workstation GPU against a data center card on the Pascal architecture: 4 GB GDDR5 against 24 GB GDDR5 and 4.2x the memory bandwidth on the P40.
At a glance
Updated 21 minutes ago- Memory
- 4 GB
- GDDR5
- Memory bandwidth
- 82 GB/s
- From
- --
- Not sold on demand · 1 provider
- Memory
- 24 GB
- GDDR5
- Memory bandwidth
- 346 GB/s
- From
- $0.11 /GPU/hr
- 1 provider
Price comparison
Cheapest listed price per GPU per hour by billing type, and the median across providers.
| Billing | P1000 | P40 | Difference |
|---|---|---|---|
| On-demand | Not sold on demand | $0.11 | |
| Spot | No spot listings | $0.07 | |
| Reserved | $0.05 | No reserved listings | |
| Median | $0.07 | $0.11 | 36% cheaper on P1000 |
Median: Median across providers, one vote each, so a large catalog does not outweigh a small one.
Price history
P1000 vs P40 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | P1000 | P40 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 4 GB GDDR5 | 24 GB GDDR5 | 6x more on P40 |
| Bandwidth | 82 GB/s | 346 GB/s | 4.2x higher on P40 |
| Bus width | 128-bit | 384-bit | 3x wider on P40 |
| Compute · dense | |||
| INT8 | Not supported | 47 TOPS | P40 only |
| FP32 | 1.8 TFLOPS | 12 TFLOPS | 6.7x higher on P40 |
| Platform | |||
| Interconnect | PCIe only | PCIe only | |
| Board power | 47 W | 250 W | 5.3x higher on P40 |
| Released | Q1 2017 | Q3 2016 | |
| Precision | |||
| Supported formats | FP16FP32 | FP16FP32INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: P1000 datasheet and P40 datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | P1000 /GPU/hr | P40 /GPU/hr |
|---|---|---|
Database Mart
|
Reserved (24mo) $0.05 | -- |
Vast.ai
|
-- | On-Demand $0.11 |
Similar GPUs
Other comparisons in the same class.
Our data for Nvidia P1000 was last updated on Sept. 7, 2026, and for Nvidia P40 on Sept. 7, 2026.