A workstation GPU against a consumer card, one Pascal and one Ada Lovelace: 2 GB GDDR5 against 24 GB GDDR6X and 13x the memory bandwidth on the RTX 4090.
At a glance
Updated 6 minutes ago- Memory
- 2 GB
- GDDR5
- Memory bandwidth
- 80 GB/s
- From
- --
- Memory
- 24 GB
- GDDR6X
- Memory bandwidth
- 1.01 TB/s
- From
- $0.23 /GPU/hr
- 17 providers
Price comparison
Cheapest listed price per GPU per hour by billing type, and the median across providers.
| Billing | P620 | RTX 4090 | Difference |
|---|---|---|---|
| On-demand | -- | $0.23 | |
| Spot | No spot listings | $0.16 | |
| Reserved | No reserved listings | $0.27 | |
| Median | -- | $0.44 |
Median: Median across providers, one vote each, so a large catalog does not outweigh a small one.
Price history
P620 vs RTX 4090 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | P620 | RTX 4090 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 2 GB GDDR5 | 24 GB GDDR6X | 12x more on RTX 4090 |
| Bandwidth | 80 GB/s | 1,010 GB/s | 13x higher on RTX 4090 |
| Bus width | 128-bit | 384-bit | 3x wider on RTX 4090 |
| Compute · dense | |||
| FP8 | Not supported | 330.3 TFLOPS | RTX 4090 only |
| FP16 / BF16 | 165.2 TFLOPS | ||
| INT8 | Not supported | 660.6 TOPS | RTX 4090 only |
| FP32 | 1.3 TFLOPS | 82.6 TFLOPS | 64x higher on RTX 4090 |
| Platform | |||
| Interconnect | PCIe only | PCIe only | |
| Board power | 40 W | 450 W | 11x higher on RTX 4090 |
| Released | Q1 2018 | Q4 2022 | 5 years newer on RTX 4090 |
| Precision | |||
| Supported formats | FP16FP32 | FP8FP16BF16TF32FP32INT4INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: P620 datasheet and RTX 4090 datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | P620 /GPU/hr | RTX 4090 /GPU/hr |
|---|---|---|
Theta EdgeCloud
|
-- | On-Demand $0.23 |
Salad
|
-- | On-Demand $0.30 |
Novita
|
-- | On-Demand $0.33 |
GPU.ai
|
-- | On-Demand $0.34 |
Runpod
|
-- | On-Demand $0.34 |
Packet·ai
|
-- | On-Demand $0.39 |
Lium
|
-- | On-Demand $0.58 |
Vast.ai
|
-- | On-Demand $4.00 |
0 providers list the P620 and 17 the RTX 4090. Every listing is on the P620 page and the RTX 4090 page.
Similar GPUs
Other comparisons in the same class.
Our data for Nvidia P620 was last updated on Sept. 7, 2026, and for Nvidia RTX 4090 on Sept. 7, 2026.