Tesla T4 vs STG

#ad 
Buy on Amazon
VS

Primary details

GPU architecture, market segment, value for money and other general parameters compared.

Place in the rankingnot rated259
Place by popularitynot in top-100not in top-100
Power efficiencyno data26.63
Architectureno dataTuring (2018−2022)
GPU code nameNV1TU104
Market segmentDesktopWorkstation
Release date30 September 1995 (30 years ago)13 September 2018 (7 years ago)
Launch price (MSRP)$249 no data

Detailed specifications

General parameters such as number of shaders, GPU core base clock and boost clock speeds, manufacturing process, texturing and calculation speed. Note that power consumption of some graphics cards can well exceed their nominal TDP, especially when overclocked.

Pipelines / CUDA coresno data2560
Core clock speed75 MHz585 MHz
Boost clock speedno data1590 MHz
Number of transistors1 million13,600 million
Manufacturing process technology500 nm12 nm
Power consumption (TDP)2 Watt70 Watt
Texture fill rate0.08254.4
Floating-point processing powerno data8.141 TFLOPS
ROPs164
TMUs1160
Tensor Coresno data320
Ray Tracing Coresno data40
L1 Cacheno data2.5 MB
L2 Cacheno data4 MB

Form factor & compatibility

Information on compatibility with other computer components. Useful when choosing a future computer configuration or upgrading an existing one. For desktop graphics cards it's interface and bus (motherboard compatibility), additional power connectors (power supply compatibility).

InterfacePCIPCIe 3.0 x16
Length168 mm168 mm
Width1-slot1-slot
Supplementary power connectorsNoneNone

VRAM capacity and type

Parameters of VRAM installed: its type, size, bus, clock and resulting bandwidth. Integrated GPUs have no dedicated video RAM and use a shared part of system RAM.

Memory typeFPMGDDR6
Maximum RAM amount1 MB16 GB
Memory bus width64 Bit256 Bit
Memory clock speed50 MHz1250 MHz
Memory bandwidth400.0 MB/s320.0 GB/s

Connectivity and outputs

This section shows the types and number of video connectors on each GPU. The data applies specifically to desktop reference models (for example, NVIDIA’s Founders Edition). OEM partners often modify both the number and types of ports. On notebook GPUs, video‐output options are determined by the laptop’s design rather than the graphics chip itself.

Display Connectors1x VGA, 1x DB13W3No outputs

API and SDK support

List of supported 3D and general-purpose computing APIs, including their specific versions.

DirectX1.012 Ultimate (12_1)
Shader Modelno data6.5
OpenGLN/A4.6
OpenCLN/A1.2
VulkanN/A1.2.131
CUDA-7.5
DLSS-+

Pros & cons summary


Recency 30 September 1995 13 September 2018
Maximum RAM amount 1 MB 16 GB
Chip lithography 500 nm 12 nm
Power consumption (TDP) 2 Watt 70 Watt

STG has 3400% lower power consumption.

Tesla T4, on the other hand, has an age advantage of 22 years, a 1638300% higher maximum VRAM amount, and a 4066.7% more advanced lithography process.

We couldn't decide between STG and Tesla T4. We've got no test results to judge.

Be aware that STG is a desktop graphics card while Tesla T4 is a workstation one.

Vote for your favorite

Do you think we are right or mistaken in our choice? Vote by clicking "Like" button near your favorite graphics card.


NVIDIA STG
STG
NVIDIA Tesla T4
Tesla T4

Other comparisons

We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.

Community ratings

Here you can see the user ratings of the compared graphics cards, as well as rate them yourself.


1.6 7 votes

Rate STG on a scale of 1 to 5:

  • 1
  • 2
  • 3
  • 4
  • 5
3.2 265 votes

Rate Tesla T4 on a scale of 1 to 5:

  • 1
  • 2
  • 3
  • 4
  • 5

Comments

Here you can give us your opinion about STG or Tesla T4, agree or disagree with our ratings, or report errors or inaccuracies on the site.