rent-a-gpu.eu

NVIDIA · Turing

Rent T4

NVIDIA T4 Tensor Core GPU, 16 GB.inference smallVirtual desktops
Full price from
—
in stock, per GPU-hour
Spot from
—
in stock, per GPU-hour
Offers in stock
0 of 19
full price or spot
Providers in stock
0 of 1
full price or spot

Offers (20)

T Cloud PublicNo stock dataSelf-serviceNot linked · PCIe only

8× T416 GB each, 128 GB total

Netherlands · 64 vCPU · 256 GB RAM

Details

Stock and price checked 6 min ago.

You start it yourself once there is stock.

This GPU has no fast GPU-to-GPU link. These are separate cards: good for separate jobs, slow for one model split across them.

pi2.16xlarge.4

Full price
€3.64
per hour, whole instance, 8 GPUs
€0.46/h per GPU
View offer
T Cloud PublicNo stock dataSelf-serviceNot linked · PCIe only

2× T416 GB each, 32 GB total

Netherlands · 16 vCPU · 64 GB RAM · 15 Gbit/s

Details

Stock and price checked 6 min ago.

You start it yourself once there is stock.

This GPU has no fast GPU-to-GPU link. These are separate cards: good for separate jobs, slow for one model split across them.

pi2.4xlarge.4

Full price
€1.24
per hour, whole instance, 2 GPUs
€0.62/h per GPU
View offer
T Cloud PublicNo stock dataSelf-service

1× T416 GB VRAM

Netherlands · 8 vCPU · 32 GB RAM · 10 Gbit/s

Details

Stock and price checked 6 min ago.

You start it yourself once there is stock.

pi2.2xlarge.4

Full price
€0.62
per hour, whole instance, 1 GPU
View offer
T Cloud PublicNo stock dataSelf-serviceNot linked · PCIe only

4× T416 GB each, 64 GB total

Netherlands · 32 vCPU · 128 GB RAM · 25 Gbit/s

Details

Stock and price checked 6 min ago.

You start it yourself once there is stock.

This GPU has no fast GPU-to-GPU link. These are separate cards: good for separate jobs, slow for one model split across them.

pi2.8xlarge.4

Full price
€2.49
per hour, whole instance, 4 GPUs
€0.62/h per GPU
View offer
T Cloud PublicNo stock dataSelf-serviceNot linked · PCIe only

2× T416 GB each, 32 GB total

Germany · 16 vCPU · 64 GB RAM · 15 Gbit/s

Details

Stock and price checked 6 min ago.

You start it yourself once there is stock.

This GPU has no fast GPU-to-GPU link. These are separate cards: good for separate jobs, slow for one model split across them.

pi2.4xlarge.4

Full price
€1.44
per hour, whole instance, 2 GPUs
€0.72/h per GPU
View offer
T Cloud PublicNo stock dataSelf-serviceNot linked · PCIe only

2× T416 GB each, 32 GB total

Germany · 16 vCPU · 64 GB RAM · 15 Gbit/s

Details

Stock and price checked 6 min ago.

You start it yourself once there is stock.

This GPU has no fast GPU-to-GPU link. These are separate cards: good for separate jobs, slow for one model split across them.

pi2.4xlarge.4

Full price
€1.44
per hour, whole instance, 2 GPUs
€0.72/h per GPU
View offer
T Cloud PublicNo stock dataSelf-serviceNot linked · PCIe only

4× T416 GB each, 64 GB total

Germany · 32 vCPU · 128 GB RAM · 25 Gbit/s

Details

Stock and price checked 6 min ago.

You start it yourself once there is stock.

This GPU has no fast GPU-to-GPU link. These are separate cards: good for separate jobs, slow for one model split across them.

pi2.8xlarge.4

Full price
€2.89
per hour, whole instance, 4 GPUs
€0.72/h per GPU
View offer
T Cloud PublicNo stock dataSelf-serviceNot linked · PCIe only

4× T416 GB each, 64 GB total

Germany · 32 vCPU · 128 GB RAM · 25 Gbit/s

Details

Stock and price checked 6 min ago.

You start it yourself once there is stock.

This GPU has no fast GPU-to-GPU link. These are separate cards: good for separate jobs, slow for one model split across them.

pi2.8xlarge.4

Full price
€2.89
per hour, whole instance, 4 GPUs
€0.72/h per GPU
View offer
Provider not namedMight be available

T4

EU · 17 offers

Full price
from €0.46
per GPU, per hour
See all 19 offers

Price and availability history

Price per GPU-hour

Excluding VAT.

Providers with stock

Each provider counts once. Full price and spot are separate.

Not enough history in this range yet. We record every 10 minutes since 9 November 2026.

Share of offers in stock

Full price. Offers we can't say are really sold there are left out until they've been in stock once.

Not enough history in this range yet. We record every 10 minutes since 9 November 2026.

Units free

No provider reports a number for this GPU.

Not enough history in this range yet. We record every 10 minutes since 9 November 2026.

Stock by provider

In stock, yes or no, for every provider selling this GPU. A filled band means in stock: green at full price, orange as spot.

Not enough history in this range yet. We record every 10 minutes since 9 November 2026.

Using several together

Can't be linked. This GPU has no NVLink, so several in one server only talk over PCIe at up to 32 GB/s. Each card keeps its own 16 GB. That suits running a separate job on each card. Splitting one model across them works, but slowly.

Specifications

Low-profile; PCIe Gen3 x16 (32 GB/s), no NVLink. Product brief lists up to 320 GB/s memory bandwidth; datasheet lists 300 GB/s.

Memory

VRAM
16 GB
Memory type
GDDR6
Memory bandwidth
How fast the GPU reaches its memory. Often limits LLM speed
320 GB/s
Bus width
256 bit
ECC memory
Detects and corrects memory errors
Yes

Compute

FP32
Speed at 32-bit precision
8.1 TFLOPS
FP16
Speed at 16-bit precision
65 TFLOPS
INT8
8-bit integer speed, used by quantized models
130 TOPS
FP8 support
No
FP4 support
No
Transformer Engine
Hardware that speeds up FP8 and FP4
No
Compute cores
2,560

Multi-GPU and connectivity

NVSwitch
Lets every GPU in a server talk to every other at full speed
No
PCIe generation
3
PCIe lanes
16
PCIe bandwidth
32 GB/s

Sharing and security

MIG partitioning
Splits one GPU into several isolated smaller GPUs
No
Max MIG instances
0
vGPU
Yes
Confidential computing
No

Hardware

Architecture
Turing
Launch year
2018
Process node
TSMC 12nm FFN
Transistors
13.6 billion
Die size
545 mm²
Power (TDP)
Maximum power draw
70 W
Cooling
passive

Video

NVENC engines
1
NVDEC engines
2
AV1 encode
No
AV1 decode
No
Sources (38)