The RTX 6000 Ada is newer, with 3x the memory and 3.2x the bandwidth. The T4 is typically cheaper.
At a glance
Memory
3x more on RTX 6000 Ada
- RTX 6000 Ada
- 48 GB
- T4
- 16 GB
Memory bandwidth
3.2x higher on RTX 6000 Ada
- RTX 6000 Ada
- 960 GB/s
- T4
- 300 GB/s
Cheapest on-demand
70% cheaper on T4
- RTX 6000 Ada
- $0.49 /GPU/hr
- T4
- $0.15 /GPU/hr
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | RTX 6000 Ada | T4 | Difference |
|---|---|---|---|
| On-demand | $0.96 /GPU/hr from $0.49 | $0.64 /GPU/hr from $0.15 | 34% cheaper on T4 |
| Reserved | -- /GPU/hr from $0.43 (3 mo) | $0.43 /GPU/hr from $0.20 (36 mo) | |
| Spot | -- /GPU/hr from $0.27 | $0.26 /GPU/hr from $0.06 |
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 reserved and spot on the RTX 6000 Ada: 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 6000 Ada vs T4 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | RTX 6000 Ada | T4 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 48 GB GDDR6 | 16 GB GDDR6 | 3x more on RTX 6000 Ada |
| Bandwidth | 960 GB/s | 300 GB/s | 3.2x higher on RTX 6000 Ada |
| Bus width | 384-bit | 256-bit | 50% wider on RTX 6000 Ada |
| Compute · dense | |||
| FP8 | 728.5 TFLOPS | Not supported | RTX 6000 Ada only |
| FP16 / BF16 | 364.2 TFLOPS | 65 TFLOPS | 5.6x higher on RTX 6000 Ada |
| INT8 | 130 TOPS | ||
| FP32 | 91.1 TFLOPS | 8.1 TFLOPS | 11x higher on RTX 6000 Ada |
| Platform | |||
| Interconnect | PCIe only | PCIe only | |
| Board power | 300 W | 70 W | 4.3x higher on RTX 6000 Ada |
| Released | Q4 2022 | Q3 2018 | 4 years newer on RTX 6000 Ada |
| Precision | |||
| Supported formats | FP8FP16BF16TF32FP32INT4INT8 | FP16FP32INT4INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: RTX 6000 Ada datasheet and T4 datasheet.
Where to rent them
Providers that rent these GPUs, with each one's cheapest rate. Providers that rent both are listed first.
| Provider | RTX 6000 Ada | T4 |
|---|---|---|
Vast.ai
USA
|
$0.49 /GPU/hr On-demand | $0.15 /GPU/hr On-demand |
GPU.ai
UAE
|
$0.65 /GPU/hr On-demand | -- |
Lium
Distributed
|
$0.69 /GPU/hr On-demand | -- |
Massed Compute
USA
|
$0.79 /GPU/hr On-demand | -- |
Sesterce
France
|
$1.07 /GPU/hr On-demand | -- |
Runcrate
USA
|
$1.26 /GPU/hr On-demand PCIe | -- |
EmpirioLabs AI
USA
|
$1.40 /GPU/hr On-demand | -- |
TensorDock
Distributed
|
$0.86 /GPU/hr On-demand | -- |
Zenlayer
USA
|
-- | $0.56 /GPU/hr On-demand PCIe |
Theta EdgeCloud
Distributed
|
-- | $0.20 /GPU/hr On-demand |
Hugging Face
USA
|
-- | $0.40 /GPU/hr On-demand |
Google Cloud
USA
|
-- | $0.42 /GPU/hr On-demand |
AWS
USA
|
-- | $0.53 /GPU/hr On-demand |
Azure
USA
|
-- | $0.53 /GPU/hr On-demand |
Cerebrium
USA
|
-- | $0.59 /GPU/hr On-demand |
14 providers list the RTX 6000 Ada and 11 the T4. Every listing is on the RTX 6000 Ada page and the T4 page.
Similar GPUs
Other comparisons in the same class.
-
Nvidia L40S
48 GB GDDR6 · data center card
From $0.38 /GPU/hr Compare -
Nvidia RTX A6000
48 GB GDDR6 · 20% less bandwidth than the RTX 6000 Ada
From $0.40 /GPU/hr Compare
-
Nvidia RTX 5880 Ada
48 GB GDDR6 · released Q1 2024
From $0.49 /GPU/hr Compare
-
Nvidia L4
24 GB GDDR6 · released Q1 2023
From $0.32 /GPU/hr Compare
Our data for Nvidia RTX 6000 Ada was last updated on Sept. 14, 2026, and for Nvidia T4 on Sept. 14, 2026.