GeForce GTX 670 vs P104 100

If you are going to buy a new graphics card and are choosing between GeForce GTX 670 and P104 100, 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 GeForce GTX 670 stacks up against P104 100, check out specs charts below.

Main Specs

  GeForce GTX 670 P104 100
Power consumption (TDP) 170 Watt
Interface PCIe 3.0 x16 PCIe 3.0 x16
Supplementary power connectors Two 6-pin 1x 8-pin
Memory type GDDR5 GDDR5X
Maximum RAM amount 2 GB 4 GB
Display Connectors 2x DVI, 1x HDMI, 1x DisplayPort No outputs
  Check Price
  • Both video cards are using PCIe 3.0 x16 interface connection to a motherboard.
  • P104 100 has 2 GB more memory, than GeForce GTX 670.
  • Both cards are used in Desktops.
  • GeForce GTX 670 is build with Kepler architecture, and P104 100 - with Pascal.
  • Core clock speed of P104 100 is 627 MHz higher, than GeForce GTX 670.
  • GeForce GTX 670 is manufactured by 28 nm process technology, and P104 100 - by 16 nm process technology.
  • P104 100 is 258 mm longer, than GeForce GTX 670.
  • Memory clock speed of P104 100 is 10002 MHz higher, than GeForce GTX 670.

Game benchmarks

high / 1080p 35−40 35−40
ultra / 1080p 21−24 21−24
QHD / 1440p 16−18 16−18
4K / 2160p 10−11 10−11
low / 720p 60−65 60−65
medium / 1080p 40−45 40−45
GeForce GTX 670 and P104 100 have the same average FPS in Assassin's Creed Odyssey.

Full Specs

  GeForce GTX 670 P104 100
Architecture Kepler Pascal
Code name GK104 GP104
Type Desktop Desktop
Release date 10 May 2012 12 December 2017
Pipelines 1344 1920
Core clock speed 980 MHz 1607 MHz
Boost Clock 980 MHz 1733 MHz
Transistor count 3,540 million 7,200 million
Manufacturing process technology 28 nm 16 nm
Texture fill rate 102.5 billion/sec 208.0
Floating-point performance 2,459.5 gflops 8,873 gflops
Length 9.5" (24.1 cm) 267 mm
Memory bus width 256-bit GDDR5 256 Bit
Memory clock speed 6.0 GB/s 10008 MHz
Memory bandwidth 192.2 GB/s 320.3 GB/s
DirectX 12 (11_0) 12 (12_1)
Shader Model 5.1 6.4
OpenGL 4.2 4.6
OpenCL 1.2 1.2
Vulkan 1.1.126 1.2.131
CUDA + 6.1
CUDA cores 1344
Bus support PCI Express 3.0
Height 4.376" (11.1 cm)
SLI options +
Multi monitor support 4 displays
HDMI +
HDCP +
Maximum VGA resolution 2048x1536
Audio input for HDMI Internal
3D Blu-Ray +
3D Gaming +
3D Vision +
Bitcoin / BTC (SHA256) 97 Mh/s
Ethereum / ETH (DaggerHashimoto) 13 Mh/s
  Check Price