A workstation GPU against a consumer card, one Turing and one Blackwell: 8 GB GDDR6 against 32 GB GDDR7 and 4.3x the memory bandwidth on the RTX 5090.
At a glance
Memory
- RTX 4000
- 8 GB
- RTX 5090
- 32 GB
4x more on RTX 5090
Memory bandwidth
- RTX 4000
- 416 GB/s
- RTX 5090
- 1,792 GB/s
4.3x higher on RTX 5090
Cheapest on-demand
- RTX 4000
- $0.56 /GPU/hr
- RTX 5090
- $0.35 /GPU/hr
38% cheaper on RTX 5090
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | RTX 4000 | RTX 5090 | Difference |
|---|---|---|---|
| On-demand | -- /GPU/hr from $0.56 | $0.72 /GPU/hr from $0.35 | |
| Reserved | No reserved listings | $0.57 /GPU/hr from $0.21 (1 mo) | |
| Spot | No spot listings | -- /GPU/hr from $0.09 |
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 on-demand on the RTX 4000 and spot on the RTX 5090: 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
RTX 4000 vs RTX 5090 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | RTX 4000 | RTX 5090 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 8 GB GDDR6 | 32 GB GDDR7 | 4x more on RTX 5090 |
| Bandwidth | 416 GB/s | 1,792 GB/s | 4.3x higher on RTX 5090 |
| Bus width | 256-bit | 512-bit | 2x wider on RTX 5090 |
| Compute · dense | |||
| FP4 | Not supported | 1,676 TFLOPS | RTX 5090 only |
| FP8 | Not supported | 419 TFLOPS | RTX 5090 only |
| FP16 / BF16 | 57 TFLOPS | 209.5 TFLOPS | 3.7x higher on RTX 5090 |
| INT8 | 838 TOPS | ||
| FP32 | 7.1 TFLOPS | 104.8 TFLOPS | 15x higher on RTX 5090 |
| Platform | |||
| Interconnect | PCIe only | PCIe only | |
| Board power | 160 W | 575 W | 3.6x higher on RTX 5090 |
| Released | Q4 2018 | Q1 2025 | 6 years newer on RTX 5090 |
| Precision | |||
| Supported formats | FP16FP32INT4INT8 | FP4FP8FP16BF16TF32FP32INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: RTX 4000 datasheet and RTX 5090 datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | RTX 4000 /GPU/hr | RTX 5090 /GPU/hr |
|---|---|---|
Paperspace
|
On-Demand $0.56 | -- |
HyperAI
|
-- | On-Demand $0.35 |
Vast.ai
|
-- | On-Demand $0.37 |
GPU.ai
|
-- | On-Demand $0.40 |
GPUhub
|
-- | On-Demand $0.46 |
Lium
|
-- | On-Demand $0.50 |
Salad
|
-- | On-Demand $0.50 |
Nova Cloud
|
-- | On-Demand $0.63 |
Runpod
|
-- | On-Demand $0.69 |
1 provider list the RTX 4000 and 21 the RTX 5090. Every listing is on the RTX 4000 page and the RTX 5090 page.
Similar GPUs
Other comparisons in the same class.
-
Nvidia RTX 4000 Ada
From $0.18 /GPU/hr Compare -
Nvidia A4000
From $0.07 /GPU/hr Compare -
Nvidia RTX 5000
From $0.60 /GPU/hr Compare -
Nvidia RTX PRO 6000
From $0.66 /GPU/hr Compare -
Nvidia RTX 4090
From $0.23 /GPU/hr Compare
Our data for Nvidia RTX 4000 was last updated on Sept. 7, 2026, and for Nvidia RTX 5090 on Sept. 7, 2026.