GeForce GTX 660 and GeForce 8800 GTX - video card comparison
Passmark - benchmark score GeForce GTX 660 vs GeForce 8800 GTX
GeForce GTX 660
4119
GeForce 8800 GTX
608
GeForce GTX 660
GeForce 8800 GTX
Architecture
Kepler (2012−2018)
Tesla (2006−2010)
GPU code name
GK106
G80
Market segment
Desktop
Desktop
Release date
September 2012
November 2006
Bus support
PCI Express 3.0
-
Interface
PCIe 3.0 x16
PCIe 1.0 x16
Supplementary power connectors
One 6-pin
2x 6-pin
SLI options
+
+
Boost clock speed
1033 MHz
-
Core clock speed
980 MHz
576 MHz
CUDA cores
960
575
Floating-point performance
1,981 gflops
345.6 gflops
Manufacturing process technology
28 nm
90 nm
Number of transistors
2,540 million
681 million
Pipelines / CUDA cores
960
128
Power consumption (TDP)
140 Watt
155 Watt
Texture fill rate
78.4 billion/sec
36.8 billion/sec
Memory type
GDDR5
GDDR3
Maximum RAM amount
2 GB
768 MB
Memory bus width
192-bit GDDR5
384 Bit
Memory clock speed
6.0 GB/s
900 MHz
Memory bandwidth
144.2 GB/s
86.4 GB/s
Display Connectors
One Dual Link DVI-I, One Dual Link DVI-D, One HDMI, One DisplayPort
2x DVI, 1x S-Video
Multi monitor support
4 displays
-
HDMI
+
-
HDCP
+
-
Maximum VGA resolution
2048x1536
-
Audio input for HDMI
Internal
-
DirectX
12 (11_0)
11.1 (10_0)
CUDA
+
+
OpenCL
1.2
1.1
OpenGL
4.3
3.3
Shader Model
5.1
4.0
Vulkan
1.1.126
N/A
3D Blu-Ray
+
-
3D Gaming
+
-
3D Vision
+
-