GeForce GTX 780 and GeForce GTX 650 - video card comparison
Passmark - benchmark score GeForce GTX 780 vs GeForce GTX 650
GeForce GTX 780
8247
GeForce GTX 650
1801
GeForce GTX 780
GeForce GTX 650
Architecture
Kepler (2012−2018)
Kepler (2012−2018)
GPU code name
GK110
GK107
Market segment
Desktop
Desktop
Release date
May 2013
September 2012
Bus support
PCI Express 3.0
PCI Express 3.0
Interface
PCIe 3.0 x16
PCIe 3.0 x16
Minimum recommended system power
600 Watt
-
Supplementary power connectors
One 8-pin and one 6-pin
One 6-pin
Boost clock speed
900 MHz
-
Core clock speed
863 MHz
1058 MHz
CUDA cores
2304
384
Floating-point performance
4,156 gflops
812.5 gflops
Manufacturing process technology
28 nm
28 nm
Number of transistors
7,080 million
1,270 million
Pipelines / CUDA cores
2304
384
Power consumption (TDP)
250 Watt
64 Watt
Maximum GPU temperature
95 °C
-
Texture fill rate
160.5 billion/sec
33.9 billion/sec
Memory type
GDDR5
GDDR5
Maximum RAM amount
3 GB
2 GB
Memory bus width
384 Bit
128-bit GDDR5
Memory clock speed
6008 MHz
5.0 GB/s
Memory bandwidth
288.4 GB/s
80.0 GB/s
Display Connectors
One Dual Link DVI-I, One Dual Link DVI-D, One HDMI, One DisplayPort
One Dual Link DVI-I, One Dual Link DVI-D, One Mini HDMI
Multi monitor support
4 displays
4 displays
HDMI
+
+
HDCP
+
+
Maximum VGA resolution
2048x1536
2048x1536
Audio input for HDMI
Internal
Internal
DirectX
12 (11_0)
12 (11_0)
CUDA
+
+
OpenCL
1.2
1.2
OpenGL
4.3
4.3
Shader Model
5.1
5.1
Vulkan
1.1.126
1.1.126
3D Blu-Ray
-
+
3D Gaming
+
+
3D Vision
+
+
3D Vision Live
+
-
Blu Ray 3D
+
-
PhysX
+
-