A consumer GPU against a data center card, one Ada Lovelace and one Turing: 24 GB GDDR6X against 16 GB GDDR6 and 3.4x the memory bandwidth on the RTX 4090.
At a glance
Memory
- RTX 4090
- 24 GB
- T4
- 16 GB
1.5x more on RTX 4090
Memory bandwidth
- RTX 4090
- 1,010 GB/s
- T4
- 300 GB/s
3.4x higher on RTX 4090
Cheapest on-demand
- RTX 4090
- $0.23 /GPU/hr
- T4
- $0.20 /GPU/hr
15% cheaper on T4
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | RTX 4090 | T4 | Difference |
|---|---|---|---|
| On-demand | $0.40 /GPU/hr from $0.23 | $0.69 /GPU/hr from $0.20 | 42% cheaper on RTX 4090 |
| Reserved | $0.46 /GPU/hr from $0.27 (12 mo) | $0.43 /GPU/hr from $0.20 (36 mo) | 7% cheaper on T4 |
| Spot | -- /GPU/hr from $0.16 | -- /GPU/hr from $0.10 |
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 spot on the RTX 4090 and spot on the T4: 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 4090 vs T4 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | RTX 4090 | T4 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 24 GB GDDR6X | 16 GB GDDR6 | 1.5x more on RTX 4090 |
| Bandwidth | 1,010 GB/s | 300 GB/s | 3.4x higher on RTX 4090 |
| Bus width | 384-bit | 256-bit | 1.5x wider on RTX 4090 |
| Compute · dense | |||
| FP8 | 330.3 TFLOPS | Not supported | RTX 4090 only |
| FP16 / BF16 | 165.2 TFLOPS | 65 TFLOPS | 2.5x higher on RTX 4090 |
| INT8 | 660.6 TOPS | 130 TOPS | 5.1x higher on RTX 4090 |
| FP32 | 82.6 TFLOPS | 8.1 TFLOPS | 10x higher on RTX 4090 |
| Platform | |||
| Interconnect | PCIe only | PCIe only | |
| Board power | 450 W | 70 W | 6.4x higher on RTX 4090 |
| Released | Q4 2022 | Q3 2018 | 4 years newer on RTX 4090 |
| Precision | |||
| Supported formats | FP8FP16BF16TF32FP32INT4INT8 | FP16FP32INT4INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: RTX 4090 datasheet and T4 datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | RTX 4090 /GPU/hr | T4 /GPU/hr |
|---|---|---|
Theta EdgeCloud
|
On-Demand $0.23 | On-Demand $0.20 |
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 | -- |
Vast.ai
|
On-Demand $0.40 | -- |
Lium
|
On-Demand $0.58 | -- |
Zenlayer
|
-- | On-Demand $0.56 |
Hugging Face
|
-- | On-Demand $0.40 |
Google Cloud
|
-- | On-Demand $0.42 |
AWS
|
-- | On-Demand $0.53 |
Azure
|
-- | On-Demand $0.53 |
Cerebrium
|
-- | On-Demand $0.59 |
Replicate
|
-- | On-Demand $0.81 |
17 providers list the RTX 4090 and 10 the T4. Every listing is on the RTX 4090 page and the T4 page.
Similar GPUs
Other comparisons in the same class.
Our data for Nvidia RTX 4090 was last updated on Sept. 7, 2026, and for Nvidia T4 on Sept. 7, 2026.