Nvidia RTX PRO 6000 vs Nvidia T4

The RTX PRO 6000 is newer, with 6x the memory and 5.3x the bandwidth. The T4 is typically cheaper.

At a glance

Memory

6x more on RTX PRO 6000

RTX PRO 6000: 96 GB

T4: 16 GB

Memory bandwidth

5.3x higher on RTX PRO 6000

RTX PRO 6000: 1,597 GB/s

T4: 300 GB/s

Cheapest on-demand

84% cheaper on T4

RTX PRO 6000: $0.65 /GPU/hr

T4: $0.10 /GPU/hr

Price comparison

Median price per GPU per hour by billing type, with the cheapest listing under it.

Billing	RTX PRO 6000	T4	Difference
On-demand	$2.18 /GPU/hr from $0.65	$0.64 /GPU/hr from $0.10	71% cheaper on T4
Reserved	$1.81 /GPU/hr from $0.48 (1 mo)	$0.43 /GPU/hr from $0.20 (36 mo)	77% cheaper on T4
Spot	$1.29 /GPU/hr from $0.34	$0.26 /GPU/hr from $0.06	80% cheaper on T4

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. Verify before provisioning. More on how we price.

Price history

RTX PRO 6000 vs T4 price history

Weekly median on-demand price per GPU per hour

Last 12 months

Aggregating historical prices...

Specs comparison

Spec	RTX PRO 6000	T4	Difference
Memory
Capacity	96 GB GDDR7	16 GB GDDR6	6x more on RTX PRO 6000
Bandwidth	1,597 GB/s	300 GB/s	5.3x 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 2018	6 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 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 PRO 6000	T4
Vast.ai USA	$1.10 /GPU/hr On-demand	$0.10 /GPU/hr On-demand
Packet·ai USA	$0.66 /GPU/hr On-demand	--
HyperAI Hong Kong	$0.80 /GPU/hr On-demand	--
GPUhub Singapore	$1.10 /GPU/hr On-demand	--
Lium Distributed	$1.19 /GPU/hr On-demand	--
GPU.ai UAE	$1.69 /GPU/hr On-demand	--
Runpod USA	$1.69 /GPU/hr On-demand	--
UpCloud Finland	$1.88 /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