GeForce GT 640M LE vs Radeon R7 M275DX

If you are going to buy a new graphics card and are choosing between GeForce GT 640M LE and Radeon R7 M275DX, 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 GT 640M LE stacks up against Radeon R7 M275DX, check out specs charts below.

GeForce GT 640M LE and Radeon R7 M275DX are Laptop Graphics Cards

Note: GeForce GT 640M LE and Radeon R7 M275DX are only used in laptop graphics. They have lower GPU clock speed compared to the desktop variant, which results in lower power consumption, but also 10-30% lower gaming performance. Check available laptop models with GeForce GT 640M LE or Radeon R7 M275DX here:

Main Specs

  GeForce GT 640M LE Radeon R7 M275DX
Power consumption (TDP) 20 Watt
Interface PCIe 2.0 x16
Memory type DDR3\DDR5 DDR3
Maximum RAM amount 2 GB
Display Connectors No outputs
  Check Price Check Price
  • Both cards are used in Laptops.
  • GeForce GT 640M LE is build with Fermi / Kepler architecture, and Radeon R7 M275DX - with GCN.
  • GeForce GT 640M LE and Radeon R7 M275DX are manufactured by 28 nm process technology.

Game benchmarks

high / 1080p 0−1 9−10
ultra / 1080p 5−6
QHD / 1440p 0−1 0−1
low / 720p 1−2 21−24
medium / 1080p 0−1 10−12
The average gaming FPS of Radeon R7 M275DX in Assassin's Creed Odyssey is 2100% more, than GeForce GT 640M LE.

Full Specs

  GeForce GT 640M LE Radeon R7 M275DX
Architecture Fermi / Kepler GCN
Code name N13P-LP
Type Laptop Laptop
Release date 22 March 2012 4 June 2014
Pipelines 384 896
Transistor count 585 million
Manufacturing process technology 28 nm 28 nm
Floating-point performance 384.0 gflops
Memory bus width 128bit
Memory clock speed 1800 - 4000 MHz
Shared memory - +
DirectX 12 API DirectX 12, Shader 5.0
Shader Model 5.1
OpenGL 4.5
OpenCL 1.1
Vulkan N/A
CUDA +
CUDA cores Up to 384
Bus support PCI Express 2.0, PCI Express 3.0
HDMI +
HDCP +
Maximum VGA resolution Up to 2048x1536
3D Blu-Ray +
Bitcoin / BTC (SHA256) 14 Mh/s
Laptop size medium sized medium sized
Optimus +
Eyefinity +
AppAcceleration +
  Check Price Check Price