NVIDIA GeForce 8800 GTS 640 vs NVIDIA GeForce 8800 GTX

Comparative analysis of NVIDIA GeForce 8800 GTS 640 and NVIDIA GeForce 8800 GTX videocards for all known characteristics in the following categories: Essentials, Technical info, Video outputs and ports, Compatibility, dimensions and requirements, API support, Memory, Technologies. Benchmark videocards performance analysis: PassMark - G3D Mark, PassMark - G2D Mark, GFXBench 4.0 - T-Rex (Frames), GFXBench 4.0 - T-Rex (Fps).

NVIDIA GeForce 8800 GTS 640

NVIDIA GeForce 8800 GTX

Differences

Reasons to consider the NVIDIA GeForce 8800 GTS 640

Around 8% lower typical power consumption: 143 Watt vs 155 Watt
Around 76% higher memory clock speed: 1584 MHz vs 900 MHz

Thermal Design Power (TDP)	143 Watt vs 155 Watt
Memory clock speed	1584 MHz vs 900 MHz

Reasons to consider the NVIDIA GeForce 8800 GTX

Around 12% higher core clock speed: 576 MHz vs 513 MHz
3x more texture fill rate: 36.8 billion / sec vs 12.31 GTexel / s
Around 33% higher pipelines: 128 vs 96
Around 52% better floating-point performance: 345.6 gflops vs 228.1 gflops
Around 20% higher maximum memory size: 768 MB vs 640 MB

Core clock speed	576 MHz vs 513 MHz
Texture fill rate	36.8 billion / sec vs 12.31 GTexel / s
Pipelines	128 vs 96
Floating-point performance	345.6 gflops vs 228.1 gflops
Maximum memory size	768 MB vs 640 MB

Compare benchmarks

GPU 1: NVIDIA GeForce 8800 GTS 640
GPU 2: NVIDIA GeForce 8800 GTX

Name	NVIDIA GeForce 8800 GTS 640	NVIDIA GeForce 8800 GTX
PassMark - G3D Mark		590
PassMark - G2D Mark		98
GFXBench 4.0 - T-Rex (Frames)		3349
GFXBench 4.0 - T-Rex (Fps)		3349

Compare specifications (specs)

	NVIDIA GeForce 8800 GTS 640	NVIDIA GeForce 8800 GTX
Essentials
Architecture	Tesla	Tesla
Code name	G80	G80
Launch date	8 November 2006	8 November 2006
Launch price (MSRP)	$449	$599
Place in performance rating	not rated	1266
Type	Desktop	Desktop
Technical info
Core clock speed	513 MHz	576 MHz
Floating-point performance	228.1 gflops	345.6 gflops
Manufacturing process technology	90 nm	90 nm
Pipelines	96	128
Texture fill rate	12.31 GTexel / s	36.8 billion / sec
Thermal Design Power (TDP)	143 Watt	155 Watt
Transistor count	681 million	681 million
CUDA cores		575
Video outputs and ports
Display Connectors	2x DVI, 1x S-Video	2x DVI, 1x S-Video
Compatibility, dimensions and requirements
Interface	PCIe 1.0 x16	PCIe 1.0 x16
Length	267 mm	270 mm
Supplementary power connectors	1x 6-pin	2x 6-pin
API support
DirectX	10.0	10.0
OpenGL	3.3	3.3
Memory
Maximum RAM amount	640 MB	768 MB
Memory bandwidth	63.4 GB / s	86.4 GB / s
Memory bus width	320 Bit	384 Bit
Memory clock speed	1584 MHz	900 MHz
Memory type	GDDR3	GDDR3
Technologies
SLI