AMD Radeon R7 250 OEM vs NVIDIA GeForce GTX 670
We compared two Desktop platform GPUs: 2GB VRAM Radeon R7 250 OEM and 2GB VRAM GeForce GTX 670 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
AMD Radeon R7 250 OEM 's Advantages
Released 1 years and 5 months late
Boost Clock has increased by 7% (1050MHz vs 980MHz)
Lower TDP (65W vs 170W)
NVIDIA GeForce GTX 670 's Advantages
Larger VRAM bandwidth (192.3GB/s vs 32.00GB/s)
960 additional rendering cores
Score
Benchmark
FP32 (float)
Radeon R7 250 OEM
0.806 TFLOPS
GeForce GTX 670
+226%
2.634 TFLOPS
Graphics Card
Oct 2013
Release Date
May 2012
Volcanic Islands
Generation
GeForce 600
Desktop
Type
Desktop
PCIe 3.0 x8
Bus Interface
PCIe 3.0 x16
Clock Speeds
1000 MHz
Base Clock
915 MHz
1050 MHz
Boost Clock
980 MHz
1000 MHz
Memory Clock
1502 MHz
Memory
2GB
Memory Size
2GB
DDR3
Memory Type
GDDR5
128bit
Memory Bus
256bit
32.00GB/s
Bandwidth
192.3GB/s
Render Config
6
Compute Units
-
-
-
-
384
Shading Units
1344
24
TMUs
112
8
ROPs
32
-
-
-
-
-
-
16 KB (per CU)
L1 Cache
16 KB (per SMX)
256 KB
L2 Cache
512 KB
-
-
-
Theoretical Performance
8.400 GPixel/s
Pixel Rate
27.44 GPixel/s
25.20 GTexel/s
Texture Rate
109.8 GTexel/s
-
-
-
806.4 GFLOPS
FP32 (float)
2.634 TFLOPS
50.40 GFLOPS
FP64 (double)
109.8 GFLOPS
Board Design
65W
TDP
170W
250 W
Suggested PSU
450 W
1x DVI
1x HDMI 1.4a
1x VGA
Outputs
2x DVI
1x HDMI 1.4a
1x DisplayPort 1.2
None
Power Connectors
2x 6-pin
Graphics Processor
Oland
GPU Name
GK104
Oland XT
(215-0837000)
GPU Variant
GK104-325-A2
GCN 1.0
Architecture
Kepler
TSMC
Foundry
TSMC
28 nm
Process Size
28 nm
0.95 billion
Transistors
3.54 billion
77 mm²
Die Size
294 mm²
Graphics Features
12 (11_1)
DirectX
12 (11_0)
4.6
OpenGL
4.6
1.2
OpenCL
3.0
1.2
Vulkan
1.1
-
CUDA
3.0
5.1
Shader Model
5.1
