Home GPU Comparison NVIDIA GeForce GTX 670 vs NVIDIA GeForce GTX 490

NVIDIA GeForce GTX 670 vs NVIDIA GeForce GTX 490

We compared two Desktop platform GPUs: 2GB VRAM GeForce GTX 670 and 1536MB VRAM GeForce GTX 490 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.

Main Differences

NVIDIA GeForce GTX 670 's Advantages
Boost Clock980MHz
More VRAM (2GB vs 1GB)
Larger VRAM bandwidth (192.3GB/s vs 164.0GB/s)
864 additional rendering cores
Lower TDP (170W vs 365W)

Score

Benchmark

FP32 (float)
GeForce GTX 670 +125%
2.634 TFLOPS
GeForce GTX 490
1.166 TFLOPS
VS

Graphics Card

May 2012
Release Date
Unknown
GeForce 600
Generation
GeForce 400
Desktop
Type
Desktop
PCIe 3.0 x16
Bus Interface
PCIe 2.0 x16

Clock Speeds

915 MHz
Base Clock
-
980 MHz
Boost Clock
-
1502 MHz
Memory Clock
854 MHz

Memory

2GB
Memory Size
1536MB
GDDR5
Memory Type
GDDR5
256bit
Memory Bus
384bit
192.3GB/s
Bandwidth
164.0GB/s

Render Config

-
SM Count
15
-
Compute Units
-
1344
Shading Units
480
112
TMUs
60
32
ROPs
48
-
Tensor Cores
-
-
RT Cores
-
16 KB (per SMX)
L1 Cache
64 KB (per SM)
512 KB
L2 Cache
768 KB

Theoretical Performance

27.44 GPixel/s
Pixel Rate
18.24 GPixel/s
109.8 GTexel/s
Texture Rate
36.48 GTexel/s
-
FP16 (half)
-
2.634 TFLOPS
FP32 (float)
1166 GFLOPS
109.8 GFLOPS
FP64 (double)
145.8 GFLOPS

Graphics Processor

GK104
GPU Name
GF100
GK104-325-A2
GPU Variant
GF100-375-A3
Kepler
Architecture
Fermi
TSMC
Foundry
TSMC
28 nm
Process Size
40 nm
3.54 billion
Transistors
3.1 billion
294 mm²
Die Size
529 mm²

Board Design

170W
TDP
365W
450 W
Suggested PSU
750 W
2x DVI 1x HDMI 1.4a 1x DisplayPort 1.2
Outputs
3x DVI 1x mini-DisplayPort
2x 6-pin
Power Connectors
2x 8-pin

Graphics Features

12 (11_0)
DirectX
12 (11_0)
4.6
OpenGL
4.6
3.0
OpenCL
1.1
1.1
Vulkan
N/A
3.0
CUDA
2.0
5.1
Shader Model
5.1

Related GPU Comparisons

© 2024 - TopCPU.net   Contact Us Privacy Policy