A data center GPU against a consumer card, one Pascal and one Ampere: 8 GB GDDR5 against 24 GB GDDR6X, 4.9x the memory bandwidth on the RTX 3090, and NVLink 112 GB/s on the RTX 3090 where the P4 is PCIe only.
At a glance
Updated 21 minutes ago- Memory
- 8 GB
- GDDR5
- Memory bandwidth
- 192 GB/s
- From
- $0.65 /GPU/hr
- 1 provider
- Memory
- 24 GB
- GDDR6X
- Memory bandwidth
- 936 GB/s
- From
- $0.10 /GPU/hr
- 10 providers
Price comparison
Cheapest listed price per GPU per hour by billing type, and the median across providers.
| Billing | P4 | RTX 3090 | Difference |
|---|---|---|---|
| On-demand | $0.65 | $0.10 | 6.5x more expensive on P4 |
| Spot | $0.12 | $0.05 | 2.5x more expensive on P4 |
| Reserved | $0.34 | $0.06 | 5.7x more expensive on P4 |
| Median | $0.81 | $0.28 | 2.9x more expensive on P4 |
Median: Median across providers, one vote each, so a large catalog does not outweigh a small one.
Price history
P4 vs RTX 3090 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | P4 | RTX 3090 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 8 GB GDDR5 | 24 GB GDDR6X | 3x more on RTX 3090 |
| Bandwidth | 192 GB/s | 936 GB/s | 4.9x higher on RTX 3090 |
| Bus width | 256-bit | 384-bit | 1.5x wider on RTX 3090 |
| Compute · dense | |||
| FP16 / BF16 | 71.2 TFLOPS | ||
| INT8 | 22 TOPS | 284.7 TOPS | 13x higher on RTX 3090 |
| FP32 | 5.5 TFLOPS | 35.6 TFLOPS | 6.5x higher on RTX 3090 |
| Platform | |||
| Interconnect | PCIe only | NVLink 112 GB/s | NVLink on RTX 3090 only |
| Board power | 75 W | 350 W | 4.7x higher on RTX 3090 |
| Released | Q3 2016 | Q3 2020 | 4 years newer on RTX 3090 |
| Precision | |||
| Supported formats | FP16FP32INT8 | FP16BF16TF32FP32INT4INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: P4 datasheet and RTX 3090 datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | P4 /GPU/hr | RTX 3090 /GPU/hr |
|---|---|---|
Google Cloud
|
On-Demand $0.65 | -- |
HyperAI
|
-- | On-Demand $0.10 |
Vast.ai
|
-- | On-Demand $0.11 |
Theta EdgeCloud
|
-- | On-Demand $0.13 |
GPU.ai
|
-- | On-Demand $0.15 |
Lium
|
-- | On-Demand $0.16 |
Runpod
|
-- | On-Demand $0.22 |
Salad
|
-- | On-Demand $0.25 |
EmpirioLabs AI
|
-- | On-Demand $0.45 |
1 provider list the P4 and 10 the RTX 3090. Every listing is on the P4 page and the RTX 3090 page.
Similar GPUs
Other comparisons in the same class.
Our data for Nvidia P4 was last updated on Sept. 7, 2026, and for Nvidia RTX 3090 on Sept. 7, 2026.