NVIDIA GRID K2 vs NVIDIA GeForce GTX 670M

Comparative analysis of NVIDIA GRID K2 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 GRID K2

  • Videocard is newer: launch date 1 year(s) 1 month(s) later
  • Around 25% higher core clock speed: 745 MHz vs 598 MHz
  • 8.8x more texture fill rate: 2x 95.36 GTexel / s billion / sec vs 33.5 billion / sec
  • 9.1x more pipelines: 2x 1536 vs 336
  • 5.7x better floating-point performance: 2x 2,289 gflops vs 803.7 gflops
  • A newer manufacturing process allows for a more powerful, yet cooler running videocard: 28 nm vs 40 nm
  • 5.4x more maximum memory size: 2x 4 GB vs 1526 MB
  • 3.3x more memory clock speed: 5000 MHz vs 1500 MHz
  • Around 56% better performance in PassMark - G3D Mark: 2737 vs 1751
  • Around 4% better performance in PassMark - G2D Mark: 319 vs 306
  • Around 63% better performance in Geekbench - OpenCL: 10550 vs 6467
  • Around 26% better performance in CompuBench 1.5 Desktop - Face Detection (mPixels/s): 18.948 vs 15.053
  • Around 65% better performance in CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s): 968.568 vs 588.645
  • Around 50% better performance in CompuBench 1.5 Desktop - T-Rex (Frames/s): 2.58 vs 1.72
  • 2.2x better performance in CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s): 114.144 vs 52.899
  • 2.3x better performance in GFXBench 4.0 - Car Chase Offscreen (Frames): 6371 vs 2731
  • 2.3x better performance in GFXBench 4.0 - Car Chase Offscreen (Fps): 6371 vs 2731
Specifications (specs)
Launch date 11 May 2013 vs 22 March 2012
Core clock speed 745 MHz vs 598 MHz
Texture fill rate 2x 95.36 GTexel / s billion / sec vs 33.5 billion / sec
Pipelines 2x 1536 vs 336
Floating-point performance 2x 2,289 gflops vs 803.7 gflops
Manufacturing process technology 28 nm vs 40 nm
Maximum memory size 2x 4 GB vs 1526 MB
Memory clock speed 5000 MHz vs 1500 MHz
Benchmarks
PassMark - G3D Mark 2737 vs 1751
PassMark - G2D Mark 319 vs 306
Geekbench - OpenCL 10550 vs 6467
CompuBench 1.5 Desktop - Face Detection (mPixels/s) 18.948 vs 15.053
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s) 968.568 vs 588.645
CompuBench 1.5 Desktop - T-Rex (Frames/s) 2.58 vs 1.72
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s) 114.144 vs 52.899
GFXBench 4.0 - Car Chase Offscreen (Frames) 6371 vs 2731
GFXBench 4.0 - Car Chase Offscreen (Fps) 6371 vs 2731

Reasons to consider the NVIDIA GeForce GTX 670M

  • 3x lower typical power consumption: 75 Watt vs 225 Watt
  • Around 9% better performance in CompuBench 1.5 Desktop - Video Composition (Frames/s): 35.916 vs 32.988
  • 10.5x better performance in GFXBench 4.0 - Manhattan (Frames): 3627 vs 344
  • 10.7x better performance in GFXBench 4.0 - T-Rex (Frames): 3346 vs 312
  • 10.5x better performance in GFXBench 4.0 - Manhattan (Fps): 3627 vs 344
  • 10.7x better performance in GFXBench 4.0 - T-Rex (Fps): 3346 vs 312
Specifications (specs)
Thermal Design Power (TDP) 75 Watt vs 225 Watt
Benchmarks
CompuBench 1.5 Desktop - Video Composition (Frames/s) 35.916 vs 32.988
GFXBench 4.0 - Manhattan (Frames) 3627 vs 344
GFXBench 4.0 - T-Rex (Frames) 3346 vs 312
GFXBench 4.0 - Manhattan (Fps) 3627 vs 344
GFXBench 4.0 - T-Rex (Fps) 3346 vs 312

Compare benchmarks

GPU 1: NVIDIA GRID K2
GPU 2: NVIDIA GeForce GTX 670M

PassMark - G3D Mark
GPU 1
GPU 2
2737
1751
PassMark - G2D Mark
GPU 1
GPU 2
319
306
Geekbench - OpenCL
GPU 1
GPU 2
10550
6467
CompuBench 1.5 Desktop - Face Detection (mPixels/s)
GPU 1
GPU 2
18.948
15.053
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)
GPU 1
GPU 2
968.568
588.645
CompuBench 1.5 Desktop - T-Rex (Frames/s)
GPU 1
GPU 2
2.58
1.72
CompuBench 1.5 Desktop - Video Composition (Frames/s)
GPU 1
GPU 2
32.988
35.916
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)
GPU 1
GPU 2
114.144
52.899
GFXBench 4.0 - Car Chase Offscreen (Frames)
GPU 1
GPU 2
6371
2731
GFXBench 4.0 - Manhattan (Frames)
GPU 1
GPU 2
344
3627
GFXBench 4.0 - T-Rex (Frames)
GPU 1
GPU 2
312
3346
GFXBench 4.0 - Car Chase Offscreen (Fps)
GPU 1
GPU 2
6371
2731
GFXBench 4.0 - Manhattan (Fps)
GPU 1
GPU 2
344
3627
GFXBench 4.0 - T-Rex (Fps)
GPU 1
GPU 2
312
3346
Name NVIDIA GRID K2 NVIDIA GeForce GTX 670M
PassMark - G3D Mark 2737 1751
PassMark - G2D Mark 319 306
Geekbench - OpenCL 10550 6467
CompuBench 1.5 Desktop - Face Detection (mPixels/s) 18.948 15.053
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s) 968.568 588.645
CompuBench 1.5 Desktop - T-Rex (Frames/s) 2.58 1.72
CompuBench 1.5 Desktop - Video Composition (Frames/s) 32.988 35.916
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s) 114.144 52.899
GFXBench 4.0 - Car Chase Offscreen (Frames) 6371 2731
GFXBench 4.0 - Manhattan (Frames) 344 3627
GFXBench 4.0 - T-Rex (Frames) 312 3346
GFXBench 4.0 - Car Chase Offscreen (Fps) 6371 2731
GFXBench 4.0 - Manhattan (Fps) 344 3627
GFXBench 4.0 - T-Rex (Fps) 312 3346
3DMark Fire Strike - Graphics Score 2062

Compare specifications (specs)

NVIDIA GRID K2 NVIDIA GeForce GTX 670M

Essentials

Architecture Kepler Fermi 2.0
Code name GK104 GF114
Launch date 11 May 2013 22 March 2012
Launch price (MSRP) $5,199
Place in performance rating 970 972
Type Workstation Laptop

Technical info

Core clock speed 745 MHz 598 MHz
Floating-point performance 2x 2,289 gflops 803.7 gflops
Manufacturing process technology 28 nm 40 nm
Pipelines 2x 1536 336
Texture fill rate 2x 95.36 GTexel / s billion / sec 33.5 billion / sec
Thermal Design Power (TDP) 225 Watt 75 Watt
Transistor count 3,540 million 1,950 million
CUDA cores 336

Video outputs and ports

Display Connectors No outputs No outputs
HDCP
HDMI
Maximum VGA resolution Up to 2048x1536

Compatibility, dimensions and requirements

Interface PCIe 3.0 x16 MXM-B (3.0)
Length 267 mm
Supplementary power connectors 1x 8-pin
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 2x 4 GB 1526 MB
Memory bandwidth 2x 160.0 GB / s 72.0 GB / s
Memory bus width 2x 256 Bit 192bit
Memory clock speed 5000 MHz 1500 MHz
Memory type GDDR5 GDDR5
Shared memory 0

Technologies

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