The RTX PRO 6000 is newer, with 6x the memory and 5x the bandwidth. The T4G is cheaper right now.
At a glance
Memory
6x more on RTX PRO 6000
- RTX PRO 6000
- 96 GB
- T4G
- 16 GB
Memory bandwidth
5x higher on RTX PRO 6000
- RTX PRO 6000
- 1,597 GB/s
- T4G
- 320 GB/s
Cheapest on-demand
35% cheaper on T4G
- RTX PRO 6000
- $0.65 /GPU/hr
- T4G
- $0.42 /GPU/hr
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | RTX PRO 6000 | T4G | Difference |
|---|---|---|---|
| On-demand | $2.07 /GPU/hr from $0.65 | -- /GPU/hr from $0.42 | |
| Reserved | $1.82 /GPU/hr from $0.48 (1 mo) | -- /GPU/hr from $0.18 (36 mo) | |
| Spot | $1.30 /GPU/hr from $0.23 | No spot listings |
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 and reserved on the T4G: 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 PRO 6000 vs T4G price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | RTX PRO 6000 | T4G | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 96 GB GDDR7 | 16 GB GDDR6 | 6x more on RTX PRO 6000 |
| Bandwidth | 1,597 GB/s | 320 GB/s | 5x higher on RTX PRO 6000 |
| Bus width | 512-bit | 256-bit | 2x wider on RTX PRO 6000 |
| Compute · dense | |||
| FP4 | 2,000 TFLOPS | Not supported | RTX PRO 6000 only |
| FP8 | 1,000 TFLOPS | Not supported | RTX PRO 6000 only |
| FP16 / BF16 | 500 TFLOPS | 65 TFLOPS | 7.7x higher on RTX PRO 6000 |
| INT8 | 1,000 TOPS | 130 TOPS | 7.7x higher on RTX PRO 6000 |
| FP32 | 120 TFLOPS | 8.1 TFLOPS | 15x higher on RTX PRO 6000 |
| Platform | |||
| Interconnect | PCIe only | PCIe only | |
| Board power | 600 W | 70 W | 8.6x higher on RTX PRO 6000 |
| Released | Q1 2025 | Q3 2020 | 5 years newer on RTX PRO 6000 |
| Precision | |||
| Supported formats | FP4FP8FP16BF16TF32FP32INT8 | FP16FP32INT4INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: RTX PRO 6000 datasheet and T4G datasheet.
Where to rent them
Providers that rent these GPUs, with each one's cheapest rate. No provider we track offers both right now.
| Provider | RTX PRO 6000 | T4G |
|---|---|---|
Packet·ai
USA
|
$0.66 /GPU/hr On-demand | -- |
HyperAI
Hong Kong
|
$0.80 /GPU/hr On-demand | -- |
Vast.ai
USA
|
$1.00 /GPU/hr On-demand | -- |
GPUhub
Singapore
|
$1.10 /GPU/hr On-demand | -- |
Lium
Distributed
|
$1.19 /GPU/hr On-demand | -- |
Runpod
USA
|
$1.64 /GPU/hr On-demand | -- |
GPU.ai
UAE
|
$1.69 /GPU/hr On-demand | -- |
UpCloud
Finland
|
$1.88 /GPU/hr On-demand | -- |
AWS
USA
|
-- | $0.42 /GPU/hr On-demand |
53 providers list the RTX PRO 6000 and 1 the T4G. Every listing is on the RTX PRO 6000 page and the T4G page.
Similar GPUs
Other comparisons in the same class.
-
Nvidia H100
80 GB HBM3 · 2.1x the bandwidth of the RTX PRO 6000
From $1.60 /GPU/hr Compare -
Nvidia B200
180 GB HBM3e · 4.8x the bandwidth of the RTX PRO 6000
From $3.75 /GPU/hr Compare
-
Nvidia H200
141 GB HBM3e · 3x the bandwidth of the RTX PRO 6000
From $2.09 /GPU/hr Compare
-
Nvidia L4
24 GB GDDR6 · released Q1 2023
From $0.27 /GPU/hr Compare
-
Nvidia T4
16 GB GDDR6 · released Q3 2018
From $0.10 /GPU/hr Compare
Our data for Nvidia RTX PRO 6000 was last updated on Sept. 14, 2026, and for Nvidia T4G on Sept. 14, 2026.