16GB GDDR6 in a 70W low-power form factor. Very low cost per hour across cloud providers. INT8 Tensor Cores for efficient inference on smaller models.

When is the T4 not a good fit?

Turing architecture lacks BF16 and FP8. 16GB VRAM limits model sizes. Slow for training. For production inference, the L4 offers significantly better throughput.

Are T4 prices going up or down?

On-demand pricing has decreased by about 8% since June 2025, dropping from $1.20 to $1.11/hr per GPU.

What size AI models can the T4 run?

With 16GB of VRAM, the T4 is best for 7B-class models in 4-bit or 8-bit quantized form, and smaller models in FP16.

How much VRAM does the T4 have?

The T4 has 16GB of VRAM. Multi-GPU setups increase total memory, but that memory is not automatically pooled across GPUs.

What is the T4's memory bandwidth?

The T4 has 300 GB/s of memory bandwidth. Higher bandwidth helps with faster data transfer between GPU memory and compute cores.

What data types does the T4 support?

The T4 supports 4 precision formats. Training: FP16, FP32. Inference: INT4, INT8.

Does the T4 support NVLink?

No. The T4 is a PCIe-only GPU with no NVLink, so it is better suited to single-GPU inference and smaller-scale workloads than large distributed training jobs.

How much does the T4 cost per hour?

T4 pricing currently ranges from $0.06/hr to $4.35/hr per GPU, depending on the provider, instance type, and billing model.

How much does the T4 cost per month?

At 720 hours per month, one T4 can cost between $40.18 to $3,133.44 per month, depending on the provider. Reserved and spot pricing can lower that further.

Which cloud providers offer the T4?

The T4 is available from 9 cloud providers, including Amazon Web Services, Lyceum, Cerebrium. Pricing and availability vary by region and billing model.

Can I rent the T4 in the cloud?

Yes. We currently track 111 T4 listings across 9 cloud providers: Billing type Listings Avg $/GPU/hr On-demand 39 $1.06/hr Reserved 54 $0.64/hr Spot 18 $0.30/hr

Nvidia T4

Low-cost inference GPU with wide cloud availability.

Compare vs other GPUs →

Aggregating historical prices...

Key Specifications

Architecture

Turing

Memory

16GB GDDR6

Memory Bandwidth

300 GB/s

Release date

Q3 2018

Compare Cloud Provider Prices

For smaller projects, the T4 is available around $0.06/hr per GPU (spot instance). This tier offers a 98% discount compared to the higher end of the market ($4.35/hr).

Billing

Max price/hr

Min GPUs

Min vCPUs

Min RAM (GB)

of shown

Default ranking

Our algorithm weighs five factors to find the most relevant matches for you:

Price: We blend total hourly price with price-per-GPU to balance affordability and value.
Specs: We favor offers with higher CPU, RAM, and GPU Memory.
Billing: We favor on-demand billing for simplicity and flexibility over spot instances, reservations, and custom quotes.
Location: We blend both datacenter proximity and provider HQ location. Datacenter location matters for latency, while HQ location matters for compliance and support.
Provider diversity: Each time a provider appears in the list, their subsequent offerings are ranked a little lower, so one provider's offerings don't crowd out the top positions.

Sorting and filtering

Click any column header to sort by that column. Use the filters above the table to narrow results by billing type, GPU count, vCPUs, or RAM. Custom sorting resets the default relevance ranking.

Transparency and funding

Ads and sponsors: Any paid placements are fixed at the top and clearly labeled as sponsored content.

Affiliates: Any affiliate links will be indicated to you as well. We may earn a commission if you click them, but this never influences the ranking order.

Provider	GPUs	Total VRAM	vCPUs	RAM	Billing	$/GPU/h	Total/h	Availability
Vast.ai Our sponsor	1x T4 1x T4 15GB (13790360)	15GB	56	96GB	On-Demand Pay-as-you-go pricing. No term commitments.	$0.15	$0.15	Available	View
Theta EdgeCloud	1x T4 1x T4 16GB (vm_gt1)	16GB	2	8GB	On-Demand Pay-as-you-go pricing. No term commitments.	$0.20	$0.20	Available	View
Azure	1x T4 1x T4 16GB (NCasT4 v3)	16GB	4	28GB	On-Demand Pay-as-you-go pricing. No term commitments.	$0.53	$0.53	Available	View
AWS	1x T4 1x T4 16GB (g4dn.xlarge)	16GB	4	16GB	On-Demand Pay-as-you-go pricing. No term commitments.	$0.53	$0.53	Available	View
Google Cloud	1x T4 1x T4 16GB (n1-standard-4-t4-1)	16GB	4	15GB	On-Demand Pay-as-you-go pricing. No term commitments.	$0.78	$0.78	Available	View
Theta EdgeCloud	2x T4 2x T4 16GB (vm_gt2)	32GB	8	16GB	On-Demand Pay-as-you-go pricing. No term commitments.	$0.20	$0.40	Available	View
Azure	1x T4 1x T4 16GB (NCasT4 v3)	16GB	8	56GB	On-Demand Pay-as-you-go pricing. No term commitments.	$0.75	$0.75	Available	View
AWS	1x T4 1x T4 16GB (g4dn.2xlarge)	16GB	8	32GB	On-Demand Pay-as-you-go pricing. No term commitments.	$0.75	$0.75	Available	View
Google Cloud	1x T4 1x T4 16GB (n1-standard-8-t4-1)	16GB	8	30GB	On-Demand Pay-as-you-go pricing. No term commitments.	$1.03	$1.03	Available	View
Lyceum	1x T4 1x T4 16GB	16GB	--	--	On-Demand Pay-as-you-go pricing. No term commitments.	$0.39	$0.39	Unknown	View
Azure	1x T4 1x T4 16GB (NCasT4 v3)	16GB	16	110GB	On-Demand Pay-as-you-go pricing. No term commitments.	$1.20	$1.20	Available	View
AWS	1x T4 1x T4 16GB (g4dn.4xlarge)	16GB	16	64GB	On-Demand Pay-as-you-go pricing. No term commitments.	$1.20	$1.20	Available	View
Google Cloud	2x T4 2x T4 16GB (n1-standard-4-t4-2)	32GB	4	15GB	On-Demand Pay-as-you-go pricing. No term commitments.	$0.66	$1.32	Available	View
Google Cloud	1x T4 1x T4 16GB (n1-standard-16-t4-1)	16GB	16	60GB	On-Demand Pay-as-you-go pricing. No term commitments.	$1.52	$1.52	Available	View
Cerebrium	1x T4 1x T4 16GB	16GB	4	16GB	On-Demand Billed per second	$0.59	$0.59	Unknown	View
Replicate	1x T4 1x T4 16GB	16GB	4	16GB	On-Demand Pay-as-you-go pricing. No term commitments.	$0.81	$0.81	Unknown	View
Lyceum	4x T4 4x T4 16GB	64GB	--	--	On-Demand Pay-as-you-go pricing. No term commitments.	$0.39	$1.56	Unknown	View
AWS	1x T4 1x T4 16GB (g4dn.8xlarge)	16GB	32	128GB	On-Demand Pay-as-you-go pricing. No term commitments.	$2.18	$2.18	Available	View
Alibaba Cloud	1x T4 1x T4 16GB (ecs.gn6i-c4g1.xlarge)	16GB	4	15GB	On-Demand Pay-as-you-go pricing. No term commitments.	$1.12	$1.12	Unknown	View
Vast.ai	1x T4 1x T4 15GB (13080903)	15GB	56	32GB	On-Demand Pay-as-you-go pricing. No term commitments.	$0.15	$0.15	Available	View
No offerings matching your filters.

Heads up: We do our best to keep these prices accurate. However, cloud costs may fluctuate based on region, usage, and other factors not listed here. These are estimates based on common setups and are for informational purposes only. Always verify current rates with the provider before provisioning.

Frequently Asked Questions

Why choose the T4?: 16GB GDDR6 in a 70W low-power form factor. Very low cost per hour across cloud providers. INT8 Tensor Cores for efficient inference on smaller models.
When is the T4 not a good fit?: Turing architecture lacks BF16 and FP8. 16GB VRAM limits model sizes. Slow for training. For production inference, the L4 offers significantly better throughput.
Are T4 prices going up or down?: On-demand pricing has decreased by about 8% since June 2025, dropping from $1.20 to $1.11/hr per GPU.
What size AI models can the T4 run?: With 16GB of VRAM, the T4 is best for 7B-class models in 4-bit or 8-bit quantized form, and smaller models in FP16.
How much VRAM does the T4 have?: The T4 has 16GB of VRAM. Multi-GPU setups increase total memory, but that memory is not automatically pooled across GPUs.
What is the T4's memory bandwidth?: The T4 has 300 GB/s of memory bandwidth. Higher bandwidth helps with faster data transfer between GPU memory and compute cores.
What data types does the T4 support?: The T4 supports 4 precision formats. Training: FP16, FP32. Inference: INT4, INT8.
Does the T4 support NVLink?: No. The T4 is a PCIe-only GPU with no NVLink, so it is better suited to single-GPU inference and smaller-scale workloads than large distributed training jobs.
How much does the T4 cost per hour?: T4 pricing currently ranges from $0.06/hr to $4.35/hr per GPU, depending on the provider, instance type, and billing model.
How much does the T4 cost per month?: At 720 hours per month, one T4 can cost between $40.18 to $3,133.44 per month, depending on the provider. Reserved and spot pricing can lower that further.
Which cloud providers offer the T4?: The T4 is available from 9 cloud providers, including Amazon Web Services, Lyceum, Cerebrium. Pricing and availability vary by region and billing model.
Can I rent the T4 in the cloud?: Yes. We currently track 111 T4 listings across 9 cloud providers:

Billing type Listings Avg $/GPU/hr

On-demand 39 $1.06/hr

Reserved 54 $0.64/hr

Spot 18 $0.30/hr

Billing type	Listings	Avg $/GPU/hr
On-demand	39	$1.06/hr
Reserved	54	$0.64/hr
Spot	18	$0.30/hr

Technical Specifications


GPU Architecture	NVIDIA Turing
NVIDIA Turing Tensor Cores	320
NVIDIA CUDA® Cores	2,560
Single-Precision	8.1 TFLOPS
Mixed-Precision (FP16/FP32)	65 TFLOPS
INT8	130 TOPS
INT4	260 TOPS
GPU Memory	16 GB GDDR6
Memory Bandwidth	300 GB/sec
ECC	Yes
Interconnect Bandwidth	32 GB/sec
System Interface	x16 PCIe Gen3
Form Factor	Low-Profile PCIe
Thermal Solution	Passive
Compute APIs	CUDA, NVIDIA TensorRT™, ONNX