Select any two GPUs for comparison

Gaming Performance Comparison

Recommended System Requirements
Game GeForce GTX 670 DirectCU II OC Edition Tesla C2075
Red Dead Redemption 2 58% 282%
Cyberpunk 2077 117% 424%
Dragon Ball Z Kakarot 2% 135%
Microsoft Flight Simulator 117% 424%
Call of Duty: Modern Warfare 58% 282%
Doom Eternal 36% 228%
FIFA 20 16% 103%
Grand Theft Auto VI 142% 483%
Need For Speed Heat 58% 282%
Halo: Reach 50% 21%

In terms of overall gaming performance, the graphical capabilities of the Nvidia GeForce GTX 670 DirectCU II OC Edition are massively better than the Nvidia Tesla C2075.

The GTX 670 was released less than a year after the Tesla C2075, and so they are likely to have similar driver support for optimizing performance when running the latest games.

The Tesla C2075 has 4096 MB more video memory than the GTX 670, so is likely to be much better at displaying game textures at higher resolutions. However, the overall memory performance is about the same.

The GTX 670 has 48.3 GB/sec greater memory bandwidth than the Tesla C2075, which means that the memory performance of the GTX 670 is noticeably better than the Tesla C2075.

The GeForce GTX 670 DirectCU II OC Edition has 1344 Shader Processing Units and the Tesla C2075 has 448. However, the actual shader performance of the GTX 670 is 1422 and the actual shader performance of the Tesla C2075 is 515. The GTX 670 having 907 better shader performance and an altogether better performance when taking into account other relevant data means that the GTX 670 delivers a massively smoother and more efficient experience when processing graphical data than the Tesla C2075.

The GTX 670 transistor size technology is 12 nm (nanometers) smaller than the Tesla C2075. This means that the GTX 670 is expected to run slightly cooler and achieve higher clock frequencies than the Tesla C2075.

The Tesla C2075 requires 247 Watts to run but there is no entry for the GTX 670. We would recommend a PSU with at least 750 Watts for the Tesla C2075, but we do not have a recommended PSU wattage for the GTX 670.

Game FPS Benchmarks On Ultra

GPU Architecture

Core Speed980 MHzvs575 MHz
Boost Clock1058 MHzvs-
ArchitectureKepler GK104-325-A2Fermi GF100
OC Potential - vs -
Driver Support Good vs Poor
Release Date01 May 2012vs01 Jul 2011
GPU LinkGD LinkGD Link

Resolution Performance

1366x768 - green tick vs green tick -
green tick vs -
green tick vs -
green tick vs -
green tick vs -

GPU Memory

Memory2048 MBvs6144 MB
Memory Speed1502 MHzvs750 MHz
Memory Bus256 Bitvs384 Bit
Memory TypeGDDR5vsGDDR5
Memory Bandwidth192.3GB/secvs144GB/sec
L2 Cache 512 KB vs green tick 768 KB
Delta Color Compression no vs no
Memory Performance 0% green tick vs green tick 0%

GPU Display

Shader Processing Units1344vs448
Actual Shader Performance68%vs25%
Texture Mapping Units112vs-
Texture Rate109.8 GTexel/svs-
Render Output Units32vs-
Pixel Rate31.4 GPixel/svs-

GPU Outputs

Max Digital Resolution (WxH)4096x2160vs2560x1600
VGA Connections0vs0
DVI Connections2vs1
HDMI Connections1vs0
DisplayPort Connections-vs-

GPU Power Requirements

Max Power-247 Watts
Recommended PSU-750 Watts

GPU Features

Shader Model5.0vs5.0
Open GL4.5vs4.5
Open CL-vs-
Notebook GPUnono

GPU Supporting Hardware

Recommended ProcessorIntel Core i5-3570K 3.4GHz-
Recommended RAM8 GB-
Maximum Recommended Gaming Resolution1920x1080-

Gaming Performance Value

Performance Value

GPU Mini Review

Mini ReviewGeForce GTX 670 DirectCU II OC Edition is a Special Edition of the powerful GeForce GTX 670. See the standard version for more information about it.
The new features include an increase in the core-clock that went from 915MHz to 980MHz while the Turbo Boost is now of 1058MHz. A 20% more effective cooler is also included.
The performance boost is significant and around 5% when compared to the standard GTX 670.
Most demanding games will run at the highest settings.
The NVIDIA Tesla C2075 companion processor is built for GPU computing. It features 448 application-acceleration cores per board, dramatically increasing performance compared to a traditional workstation. By adding a Tesla companion processor, engineers, designers, and content creation professionals can add over one Teraflop of computing potential to their workstation.
Recommended CPU
Possible GPU Upgrades
GPU Variants