Radeon HD 6670 vs GeForce GTX 480
We compared two Desktop platform GPUs: 1024MB VRAM Radeon HD 6670 and 1536MB VRAM GeForce GTX 480 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
Radeon HD 6670 's Advantages
Released 1 years and 1 months late
Lower TDP (66W vs 250W)
GeForce GTX 480 's Advantages
More VRAM (1536GB vs 1024GB)
Larger VRAM bandwidth (177.4GB/s vs 64.00GB/s)
Score
Benchmark
FP32 (float)
Radeon HD 6670
768
GeForce GTX 480
+75%
1345
Graphics Card
Apr 2011
Release Date
Mar 2010
Northern Islands
Generation
GeForce 400
Desktop
Type
Desktop
PCIe 2.0 x16
Bus Interface
PCIe 2.0 x16
Clock Speeds
1000 MHz
Memory Clock
924 MHz
Memory
1024MB
Memory Size
1536MB
GDDR5
Memory Type
GDDR5
128bit
Memory Bus
384bit
64.00GB/s
Bandwidth
177.4GB/s
Render Config
6
Compute Units
-
-
SM Count
15
480
Shading Units
480
24
TMUs
60
8
ROPs
48
8 KB (per CU)
L1 Cache
64 KB (per SM)
256 KB
L2 Cache
768 KB
Theoretical Performance
6.400 GPixel/s
Pixel Rate
21.03 GPixel/s
19.20 GTexel/s
Texture Rate
42.06 GTexel/s
768.0 GFLOPS
FP32 (float)
1345 GFLOPS
-
FP64 (double)
168.1 GFLOPS
Board Design
66W
TDP
250W
250 W
Suggested PSU
600 W
1x DVI
1x HDMI 1.3a
1x VGA
Outputs
2x DVI
1x mini-HDMI 1.3a
None
Power Connectors
1x 6-pin + 1x 8-pin
Graphics Processor
Turks
GPU Name
GF100
Turks XT
(215-0803000)
GPU Variant
GF100-375-A3
TeraScale 2
Architecture
Fermi
TSMC
Foundry
TSMC
40 nm
Process Size
40 nm
0.716 billion
Transistors
3.1 billion
118 mm²
Die Size
529 mm²
Graphics Features
11.2 (11_0)
DirectX
12 (11_0)
4.4
OpenGL
4.6
1.2
OpenCL
1.1
N/A
Vulkan
N/A
-
CUDA
2.0
5.0
Shader Model
5.1