Radeon Pro SSG vs Tesla T4

If you are going to buy a new graphics card and are choosing between Radeon Pro SSG and Tesla T4, there are a couple of things to consider. Cards with more VRAM in general perform better and allow you to play on higher graphics settings. Size also makes a difference. A model with a large heatsink can occupy up to three expansion slots on a motherboard. Be sure you have enough room in your PC case. When comparing GPUs with different architectures, more processing cores and even higher TFLOPS will not always translate to better performance. To help you decide which GPU you need, we have measured frame rates in a number of popular games. For more on how the Radeon Pro SSG stacks up against Tesla T4, check out specs charts below.
Radeon Pro SSG
Tesla T4

Main Specs

  Radeon Pro SSG Tesla T4
Power consumption (TDP) 350 Watt 70 Watt
Interface PCIe 3.0 x16 PCIe 3.0 x16
Supplementary power connectors 1x 6-pin + 1x 8-pin None
Memory type HBM2 GDDR6
Maximum RAM amount 16 GB 16 GB
Display Connectors 6x mini-DisplayPort No outputs
 
  • Radeon Pro SSG has 400% more power consumption, than Tesla T4.
  • Both video cards are using PCIe 3.0 x16 interface connection to a motherboard.
  • Radeon Pro SSG and Tesla T4 have maximum RAM of 16 GB.
  • Both cards are used in Desktops.
  • Radeon Pro SSG is build with GCN 5.0 architecture, and Tesla T4 - with Turing.
  • Core clock speed of Radeon Pro SSG is 855 MHz higher, than Tesla T4.
  • Radeon Pro SSG is manufactured by 14 nm process technology, and Tesla T4 - by 12 nm process technology.
  • Radeon Pro SSG is 99 mm longer, than Tesla T4.
  • Memory clock speed of Tesla T4 is 8110 MHz higher, than Radeon Pro SSG.

Game benchmarks

high / 1080p 50−55 35−40
ultra / 1080p 35−40 21−24
QHD / 1440p 27−30 16−18
4K / 2160p 16−18 10−11
low / 720p 80−85 60−65
medium / 1080p 60−65 40−45
The average gaming FPS of Radeon Pro SSG in Assassin's Creed Odyssey is 43% more, than Tesla T4.

Full Specs

  Radeon Pro SSG Tesla T4
Architecture GCN 5.0 Turing
Code name Vega 10 TU104
Type Workstation Workstation
Release date 8 August 2017 13 September 2018
Pipelines 4096 2560
Core clock speed 1440 MHz 585 MHz
Boost Clock 1500 MHz 1590 MHz
Transistor count 12,500 million 13,600 million
Manufacturing process technology 14 nm 12 nm
Texture fill rate 384.0 254.4
Floating-point performance 12,288 gflops
Length 267 mm 168 mm
Memory bus width 2048 Bit 256 Bit
Memory clock speed 1890 MHz 10000 MHz
Memory bandwidth 483.8 GB/s 320.0 GB/s
DirectX 12 (12_1) 12 Ultimate (12_1)
Shader Model 6.4 6.5
OpenGL 4.6 4.6
OpenCL 2.0 1.2
Vulkan 1.1.125 1.2.131
CUDA 7.5