GeForce GTX 670 vs Radeon R9 390X

Find out if it is worth upgrading your current GPU setup by comparing GeForce GTX 670 and Radeon R9 390X. Here you can take a closer look at graphics cards specs, such as core clock speed, memory type and size, display connectors, etc. The price, overall benchmark and gaming performances are usually defining factors when it comes to choosing between GeForce GTX 670 and Radeon R9 390X. Make sure that the graphics card has compatible dimensions and will properly fit in your new or current computer case. Also these graphics cards may have different system power recommendations, so take that into consideration and upgrade your PSU if necessary.

Main Specs

  GeForce GTX 670 Radeon R9 390X
Power consumption (TDP) 170 Watt 275 Watt
Interface PCIe 3.0 x16 PCIe 3.0 x16
Supplementary power connectors Two 6-pin 1 x 6-pin, 1 x 8-pin
Memory type GDDR5 GDDR5
Maximum RAM amount 2 GB
Display Connectors 2x DVI, 1x HDMI, 1x DisplayPort 2x DVI, 1x HDMI, 1x DisplayPort
  Check Price Check Price
  • Radeon R9 390X has 61% more power consumption, than GeForce GTX 670.
  • Both video cards are using PCIe 3.0 x16 interface connection to a motherboard.
  • Both cards are used in Desktops.
  • GeForce GTX 670 is build with Kepler architecture, and Radeon R9 390X - with GCN.
  • GeForce GTX 670 and Radeon R9 390X are manufactured by 28 nm process technology.
  • Radeon R9 390X is 266 mm longer, than GeForce GTX 670.
  • Memory clock speed of Radeon R9 390X is 1044 MHz higher, than GeForce GTX 670.

Game benchmarks

high / 1080p 35−40 50−55
ultra / 1080p 21−24 30−35
QHD / 1440p 16−18 24−27
4K / 2160p 10−11 14−16
low / 720p 60−65 75−80
medium / 1080p 40−45 55−60
The average gaming FPS of Radeon R9 390X in Assassin's Creed Odyssey is 34% more, than GeForce GTX 670.

Full Specs

  GeForce GTX 670 Radeon R9 390X
Architecture Kepler GCN
Code name GK104 Grenada XT
Type Desktop Desktop
Release date 10 May 2012 16 June 2015
Pipelines 1344 2816
Core clock speed 980 MHz
Boost Clock 980 MHz 1050 MHz
Transistor count 3,540 million 6,200 million
Manufacturing process technology 28 nm 28 nm
Texture fill rate 102.5 billion/sec 184.8
Floating-point performance 2,459.5 gflops 5,914 gflops
Length 9.5" (24.1 cm) 275 mm
Memory bus width 256-bit GDDR5 512 Bit
Memory clock speed 6.0 GB/s 1050 MHz
Memory bandwidth 192.2 GB/s 384 GB/s
Shared memory -
DirectX 12 (11_0)
Shader Model 5.1 6.3
OpenGL 4.2 4.6
OpenCL 1.2 2.0
Vulkan 1.1.126 +
CUDA +
FreeSync +
CUDA cores 1344
Bus support PCI Express 3.0 PCIe 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 684 Mh/s
Eyefinity +
PowerTune +
TrueAudio +
Mantle +
Design reference
Bridgeless CrossFire +
Number of Eyefinity displays 6
DisplayPort support +
CrossFire +
VCE +
DDMA audio +
Ethereum / ETH (DaggerHashimoto) 13 Mh/s 27.5 Mh/s
High bandwidth memory (HBM) -
  Check Price Check Price