A consumer GPU against a data center card, one Blackwell and one Turing: 32 GB GDDR7 against 16 GB GDDR6 and 5.6x the memory bandwidth on the RTX 5090.
At a glance
Updated 6 minutes ago- Memory
- 32 GB
- GDDR7
- Memory bandwidth
- 1.79 TB/s
- From
- $0.35 /GPU/hr
- 20 providers
- Memory
- 16 GB
- GDDR6
- Memory bandwidth
- 320 GB/s
- From
- $0.42 /GPU/hr
- 1 provider
Price comparison
Cheapest listed price per GPU per hour by billing type, and the median across providers.
| Billing | RTX 5090 | T4G | Difference |
|---|---|---|---|
| On-demand | $0.35 | $0.42 | 17% cheaper on RTX 5090 |
| Spot | $0.20 | No spot listings | |
| Reserved | $0.21 | $0.18 | 14% cheaper on T4G |
| Median | $0.68 | $1.10 | 39% cheaper on RTX 5090 |
Median: Median across providers, one vote each, so a large catalog does not outweigh a small one.
Price history
RTX 5090 vs T4G price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | RTX 5090 | T4G | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 32 GB GDDR7 | 16 GB GDDR6 | 2x more on RTX 5090 |
| Bandwidth | 1,792 GB/s | 320 GB/s | 5.6x higher on RTX 5090 |
| Bus width | 512-bit | 256-bit | 2x wider on RTX 5090 |
| Compute · dense | |||
| FP4 | 1,676 TFLOPS | Not supported | RTX 5090 only |
| FP8 | 419 TFLOPS | Not supported | RTX 5090 only |
| FP16 / BF16 | 209.5 TFLOPS | 65 TFLOPS | 3.2x higher on RTX 5090 |
| INT8 | 838 TOPS | 130 TOPS | 6.4x higher on RTX 5090 |
| FP32 | 104.8 TFLOPS | 8.1 TFLOPS | 13x higher on RTX 5090 |
| Platform | |||
| Interconnect | PCIe only | PCIe only | |
| Board power | 575 W | 70 W | 8.2x higher on RTX 5090 |
| Released | Q1 2025 | Q3 2020 | 4 years newer on RTX 5090 |
| Precision | |||
| Supported formats | FP4FP8FP16BF16TF32FP32INT8 | FP16FP32INT4INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: RTX 5090 datasheet and T4G datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | RTX 5090 /GPU/hr | T4G /GPU/hr |
|---|---|---|
HyperAI
|
On-Demand $0.35 | -- |
Salad
|
On-Demand $0.45 | -- |
GPUhub
|
On-Demand $0.46 | -- |
Lium
|
On-Demand $0.50 | -- |
Vast.ai
|
On-Demand $0.51 | -- |
GPU.ai
|
On-Demand $0.52 | -- |
Nova Cloud
|
On-Demand $0.63 | -- |
Theta EdgeCloud
|
On-Demand $0.82 | -- |
AWS
|
-- | On-Demand $0.42 |
20 providers list the RTX 5090 and 1 the T4G. Every listing is on the RTX 5090 page and the T4G page.
Similar GPUs
Other comparisons in the same class.
Our data for Nvidia RTX 5090 was last updated on Sept. 7, 2026, and for Nvidia T4G on Sept. 7, 2026.