HD Graphics 630 vs Tesla C2070

If you are going to buy a new graphics card and are choosing between HD Graphics 630 and Tesla C2070, 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 HD Graphics 630 stacks up against Tesla C2070, check out specs charts below.
HD Graphics 630
Tesla C2070

Main Specs

  HD Graphics 630 Tesla C2070
Power consumption (TDP) 15 Watt 238 Watt
Interface PCIe 3.0 x1 PCIe 2.0 x16
Supplementary power connectors 1x 8-pin
Memory type DDR3L/LPDDR3/LPDDR4 GDDR5
Maximum RAM amount 64 GB 6 GB
Display Connectors No outputs 1x DVI
 
  • Tesla C2070 has 1486% more power consumption, than HD Graphics 630.
  • HD Graphics 630 is connected by PCIe 3.0 x1, and Tesla C2070 uses PCIe 2.0 x16 interface.
  • HD Graphics 630 has 58 GB more memory, than Tesla C2070.
  • Both cards are used in Desktops.
  • HD Graphics 630 is build with Gen. 9.5 Kaby Lake architecture, and Tesla C2070 - with Fermi.
  • Core clock speed of Tesla C2070 is 274 MHz higher, than HD Graphics 630.
  • HD Graphics 630 is manufactured by 14 nm process technology, and Tesla C2070 - by 40 nm process technology.

Game benchmarks

high / 1080p 3−4 16−18
ultra / 1080p 1−2 9−10
QHD / 1440p 0−1 3−4
low / 720p 14−16 30−35
medium / 1080p 5−6 21−24
The average gaming FPS of Tesla C2070 in Assassin's Creed Odyssey is 233% more, than HD Graphics 630.

Full Specs

  HD Graphics 630 Tesla C2070
Architecture Gen. 9.5 Kaby Lake Fermi
Code name Kaby-Lake-H-GT2 GF100
Type Desktop Workstation
Release date 1 January 2017 25 July 2011
Pipelines 24 448
Core clock speed 300 MHz 574 MHz
Boost Clock 1150 MHz
Transistor count 189 million 3,100 million
Manufacturing process technology 14 nm 40 nm
Texture fill rate 26.40 32.14
Floating-point performance 441.6 gflops 1,030.4 gflops
Length 248 mm
Memory bus width 64/128 Bit 384 Bit
Memory clock speed 2988 MHz
Memory bandwidth 143.4 GB/s
Shared memory +
DirectX 12 (12_1) 12 (11_0)
Shader Model 6.4 5.1
OpenGL 4.6 4.6
OpenCL 2.1 1.1
Vulkan 1.1.103 N/A
CUDA 2.0
Quick Sync +