A workstation GPU against a data center card on the Turing architecture: 24 GB GDDR6 against 16 GB GDDR6, 2.2x the memory bandwidth on the Quadro RTX 6000, and NVLink 100 GB/s on the Quadro RTX 6000 where the T4 is PCIe only.
At a glance
Memory
- Quadro RTX 6000
- 24 GB
- T4
- 16 GB
1.5x more on Quadro RTX 6000
Memory bandwidth
- Quadro RTX 6000
- 672 GB/s
- T4
- 300 GB/s
2.2x higher on Quadro RTX 6000
Cheapest on-demand
- Quadro RTX 6000
- $1.50 /GPU/hr
- T4
- $0.15 /GPU/hr
10x more expensive on Quadro RTX 6000
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | Quadro RTX 6000 | T4 | Difference |
|---|---|---|---|
| On-demand | -- /GPU/hr from $1.50 | $0.64 /GPU/hr from $0.15 | |
| Reserved | No reserved listings | $0.43 /GPU/hr from $0.20 (36 mo) | |
| Spot | No spot listings | $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 on-demand on the Quadro RTX 6000: 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
Quadro RTX 6000 vs T4 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | Quadro RTX 6000 | T4 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 24 GB GDDR6 | 16 GB GDDR6 | 1.5x more on Quadro RTX 6000 |
| Bandwidth | 672 GB/s | 300 GB/s | 2.2x higher on Quadro RTX 6000 |
| Bus width | 384-bit | 256-bit | 1.5x wider on Quadro RTX 6000 |
| Compute · dense | |||
| FP16 / BF16 | 130.5 TFLOPS | 65 TFLOPS | 2x higher on Quadro RTX 6000 |
| INT8 | 261 TOPS | 130 TOPS | 2x higher on Quadro RTX 6000 |
| FP32 | 16.3 TFLOPS | 8.1 TFLOPS | 2x higher on Quadro RTX 6000 |
| Platform | |||
| Interconnect | NVLink 100 GB/s | PCIe only | NVLink on Quadro RTX 6000 only |
| Board power | 295 W | 70 W | 4.2x higher on Quadro RTX 6000 |
| Released | Q3 2018 | Q3 2018 | |
| Precision | |||
| Supported formats | FP16FP32INT4INT8 | FP16FP32INT4INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: Quadro RTX 6000 datasheet and T4 datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | Quadro RTX 6000 /GPU/hr | T4 /GPU/hr |
|---|---|---|
Akamai Cloud
|
On-Demand $1.50 | -- |
Lambda Labs
|
On-Demand $0.69 | -- |
Vast.ai
|
-- | On-Demand $0.15 |
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 |
2 providers list the Quadro RTX 6000 and 11 the T4. Every listing is on the Quadro RTX 6000 page and the T4 page.
Similar GPUs
Other comparisons in the same class.
-
Nvidia RTX 6000 Ada
From $0.55 /GPU/hr Compare -
Nvidia RTX A6000
From $0.35 /GPU/hr Compare -
Nvidia RTX 5000
From $0.60 /GPU/hr Compare -
Nvidia L40S
From $0.38 /GPU/hr Compare
Our data for Nvidia Quadro RTX 6000 was last updated on Sept. 7, 2026, and for Nvidia T4 on Sept. 7, 2026.