NVIDIA GeForce GTX 645 OEM vs NVIDIA GeForce GTX 670M

Comparative analysis of NVIDIA GeForce GTX 645 OEM and NVIDIA GeForce GTX 670M 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, Geekbench - OpenCL, CompuBench 1.5 Desktop - Face Detection (mPixels/s), CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s), CompuBench 1.5 Desktop - T-Rex (Frames/s), CompuBench 1.5 Desktop - Video Composition (Frames/s), CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s), GFXBench 4.0 - Car Chase Offscreen (Frames), GFXBench 4.0 - Manhattan (Frames), GFXBench 4.0 - T-Rex (Frames), GFXBench 4.0 - Car Chase Offscreen (Fps), GFXBench 4.0 - Manhattan (Fps), GFXBench 4.0 - T-Rex (Fps), 3DMark Fire Strike - Graphics Score.

 

Differences

Reasons to consider the NVIDIA GeForce GTX 645 OEM

  • Videocard is newer: launch date 1 year(s) 1 month(s) later
  • Around 38% higher core clock speed: 824 MHz vs 598 MHz
  • Around 18% higher texture fill rate: 39.55 GTexel / s vs 33.5 billion / sec
  • Around 71% higher pipelines: 576 vs 336
  • Around 18% better floating-point performance: 949.2 gflops vs 803.7 gflops
  • A newer manufacturing process allows for a more powerful, yet cooler running videocard: 28 nm vs 40 nm
  • Around 15% lower typical power consumption: 65 Watt vs 75 Watt
  • 2.7x more memory clock speed: 4000 MHz vs 1500 MHz
  • Around 8% better performance in PassMark - G3D Mark: 1882 vs 1746
  • Around 42% better performance in PassMark - G2D Mark: 431 vs 303
Specifications (specs)
Launch date 22 April 2013 vs 22 March 2012
Core clock speed 824 MHz vs 598 MHz
Texture fill rate 39.55 GTexel / s vs 33.5 billion / sec
Pipelines 576 vs 336
Floating-point performance 949.2 gflops vs 803.7 gflops
Manufacturing process technology 28 nm vs 40 nm
Thermal Design Power (TDP) 65 Watt vs 75 Watt
Memory clock speed 4000 MHz vs 1500 MHz
Benchmarks
PassMark - G3D Mark 1882 vs 1746
PassMark - G2D Mark 431 vs 303

Reasons to consider the NVIDIA GeForce GTX 670M

  • Around 49% higher maximum memory size: 1526 MB vs 1 GB
  • Around 22% better performance in Geekbench - OpenCL: 6392 vs 5238
  • Around 9% better performance in CompuBench 1.5 Desktop - Face Detection (mPixels/s): 15.053 vs 13.806
  • Around 8% better performance in CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s): 588.645 vs 546.51
  • Around 12% better performance in CompuBench 1.5 Desktop - T-Rex (Frames/s): 1.72 vs 1.535
  • Around 30% better performance in CompuBench 1.5 Desktop - Video Composition (Frames/s): 35.916 vs 27.524
  • Around 37% better performance in CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s): 52.899 vs 38.664
  • Around 90% better performance in GFXBench 4.0 - Car Chase Offscreen (Frames): 2731 vs 1435
  • Around 3% better performance in GFXBench 4.0 - Manhattan (Frames): 3627 vs 3531
  • Around 1% better performance in GFXBench 4.0 - T-Rex (Frames): 3346 vs 3300
  • Around 90% better performance in GFXBench 4.0 - Car Chase Offscreen (Fps): 2731 vs 1435
  • Around 3% better performance in GFXBench 4.0 - Manhattan (Fps): 3627 vs 3531
  • Around 1% better performance in GFXBench 4.0 - T-Rex (Fps): 3346 vs 3300
Specifications (specs)
Maximum memory size 1526 MB vs 1 GB
Benchmarks
Geekbench - OpenCL 6392 vs 5238
CompuBench 1.5 Desktop - Face Detection (mPixels/s) 15.053 vs 13.806
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s) 588.645 vs 546.51
CompuBench 1.5 Desktop - T-Rex (Frames/s) 1.72 vs 1.535
CompuBench 1.5 Desktop - Video Composition (Frames/s) 35.916 vs 27.524
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s) 52.899 vs 38.664
GFXBench 4.0 - Car Chase Offscreen (Frames) 2731 vs 1435
GFXBench 4.0 - Manhattan (Frames) 3627 vs 3531
GFXBench 4.0 - T-Rex (Frames) 3346 vs 3300
GFXBench 4.0 - Car Chase Offscreen (Fps) 2731 vs 1435
GFXBench 4.0 - Manhattan (Fps) 3627 vs 3531
GFXBench 4.0 - T-Rex (Fps) 3346 vs 3300

Compare benchmarks

GPU 1: NVIDIA GeForce GTX 645 OEM
GPU 2: NVIDIA GeForce GTX 670M

PassMark - G3D Mark
GPU 1
GPU 2
1882
1746
PassMark - G2D Mark
GPU 1
GPU 2
431
303
Geekbench - OpenCL
GPU 1
GPU 2
5238
6392
CompuBench 1.5 Desktop - Face Detection (mPixels/s)
GPU 1
GPU 2
13.806
15.053
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)
GPU 1
GPU 2
546.51
588.645
CompuBench 1.5 Desktop - T-Rex (Frames/s)
GPU 1
GPU 2
1.535
1.72
CompuBench 1.5 Desktop - Video Composition (Frames/s)
GPU 1
GPU 2
27.524
35.916
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)
GPU 1
GPU 2
38.664
52.899
GFXBench 4.0 - Car Chase Offscreen (Frames)
GPU 1
GPU 2
1435
2731
GFXBench 4.0 - Manhattan (Frames)
GPU 1
GPU 2
3531
3627
GFXBench 4.0 - T-Rex (Frames)
GPU 1
GPU 2
3300
3346
GFXBench 4.0 - Car Chase Offscreen (Fps)
GPU 1
GPU 2
1435
2731
GFXBench 4.0 - Manhattan (Fps)
GPU 1
GPU 2
3531
3627
GFXBench 4.0 - T-Rex (Fps)
GPU 1
GPU 2
3300
3346
Name NVIDIA GeForce GTX 645 OEM NVIDIA GeForce GTX 670M
PassMark - G3D Mark 1882 1746
PassMark - G2D Mark 431 303
Geekbench - OpenCL 5238 6392
CompuBench 1.5 Desktop - Face Detection (mPixels/s) 13.806 15.053
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s) 546.51 588.645
CompuBench 1.5 Desktop - T-Rex (Frames/s) 1.535 1.72
CompuBench 1.5 Desktop - Video Composition (Frames/s) 27.524 35.916
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s) 38.664 52.899
GFXBench 4.0 - Car Chase Offscreen (Frames) 1435 2731
GFXBench 4.0 - Manhattan (Frames) 3531 3627
GFXBench 4.0 - T-Rex (Frames) 3300 3346
GFXBench 4.0 - Car Chase Offscreen (Fps) 1435 2731
GFXBench 4.0 - Manhattan (Fps) 3531 3627
GFXBench 4.0 - T-Rex (Fps) 3300 3346
3DMark Fire Strike - Graphics Score 2062

Compare specifications (specs)

NVIDIA GeForce GTX 645 OEM NVIDIA GeForce GTX 670M

Essentials

Architecture Kepler Fermi 2.0
Code name GK106 GF114
Launch date 22 April 2013 22 March 2012
Place in performance rating 976 979
Type Desktop Laptop

Technical info

Core clock speed 824 MHz 598 MHz
Floating-point performance 949.2 gflops 803.7 gflops
Manufacturing process technology 28 nm 40 nm
Pipelines 576 336
Texture fill rate 39.55 GTexel / s 33.5 billion / sec
Thermal Design Power (TDP) 65 Watt 75 Watt
Transistor count 2,540 million 1,950 million
CUDA cores 336

Video outputs and ports

Display Connectors 1x DVI, 1x HDMI, 1x DisplayPort No outputs
HDCP
HDMI
Maximum VGA resolution Up to 2048x1536

Compatibility, dimensions and requirements

Interface PCIe 3.0 x16 MXM-B (3.0)
Length 147 mm
Supplementary power connectors None
Bus support PCI Express 2.0
Laptop size large
SLI options 2-way

API support

DirectX 12.0 (11_0) 12 API
OpenGL 4.6 4.5
OpenCL 1.1

Memory

Maximum RAM amount 1 GB 1526 MB
Memory bandwidth 64 GB / s 72.0 GB / s
Memory bus width 128 Bit 192bit
Memory clock speed 4000 MHz 1500 MHz
Memory type GDDR5 GDDR5
Shared memory 0

Technologies

3D Vision
3D Vision / 3DTV Play
Adaptive VSync
CUDA
FXAA
SLI