A consumer GPU against a data center card on the Turing architecture: 8 GB GDDR6 against 16 GB GDDR6, 49% more memory bandwidth on the RTX 2080, and NVLink 50 GB/s on the RTX 2080 where the T4 is PCIe only.
At a glance
Updated 8 minutes ago- Memory
- 8 GB
- GDDR6
- Memory bandwidth
- 448 GB/s
- From
- $0.08 /GPU/hr
- 1 provider
- Memory
- 16 GB
- GDDR6
- Memory bandwidth
- 300 GB/s
- From
- $0.20 /GPU/hr
- 10 providers
Price comparison
Cheapest listed price per GPU per hour by billing type, and the median across providers.
| Billing | RTX 2080 | T4 | Difference |
|---|---|---|---|
| On-demand | $0.08 | $0.20 | 2.5x more expensive on T4 |
| Spot | $0.05 | $0.10 | 2.1x more expensive on T4 |
| Reserved | No reserved listings | $0.20 | |
| Median | $0.08 | $0.69 | 8.6x more expensive on T4 |
Median: Median across providers, one vote each, so a large catalog does not outweigh a small one.
Price history
RTX 2080 vs T4 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | RTX 2080 | T4 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 8 GB GDDR6 | 16 GB GDDR6 | 2x more on T4 |
| Bandwidth | 448 GB/s | 300 GB/s | 1.5x higher on RTX 2080 |
| Bus width | 256-bit | 256-bit | Identical |
| Compute · dense | |||
| FP16 / BF16 | 40.3 TFLOPS | 65 TFLOPS | 1.6x higher on T4 |
| INT8 | 161.1 TOPS | 130 TOPS | 1.2x higher on RTX 2080 |
| FP32 | 10 TFLOPS | 8.1 TFLOPS | 1.2x higher on RTX 2080 |
| Platform | |||
| Interconnect | NVLink 50 GB/s | PCIe only | NVLink on RTX 2080 only |
| Board power | 215 W | 70 W | 3.1x higher on RTX 2080 |
| Released | Q3 2018 | Q3 2018 | |
| Precision | |||
| Supported formats | FP16FP32INT4INT8 | FP16FP32INT4INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: RTX 2080 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 2080 /GPU/hr | T4 /GPU/hr |
|---|---|---|
Salad
|
On-Demand $0.08 | -- |
Zenlayer
|
-- | On-Demand $0.56 |
Theta EdgeCloud
|
-- | On-Demand $0.20 |
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 |
1 provider list the RTX 2080 and 10 the T4. Every listing is on the RTX 2080 page and the T4 page.
Similar GPUs
Other comparisons in the same class.
Our data for Nvidia RTX 2080 was last updated on Sept. 7, 2026, and for Nvidia T4 on Sept. 7, 2026.