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