NVIDIA GeForce GTX 660 vs AMD Radeon Pro W6400

GPU · Specs Compare

Products
GPU NVIDIA GeForce GTX 660 NVIDIA · 2012-09
GPU AMD Radeon Pro W6400 AMD · 2022-01
Graphics Card
Release Date
Sep 2012
Jan 2022
Generation
GeForce 600
Radeon Pro
Type
Desktop
Desktop
Bus Interface
PCIe 3.0 x16
PCIe 4.0 x4
Clock Speeds
Base Clock
980 MHz
2331 MHz
Boost Clock
1032 MHz
2331 MHz
Memory Clock
1502 MHz
1750 MHz
Memory
Memory Size
2GB
4GB
Memory Type
GDDR5
GDDR6
Memory Bus
192bit
64bit
Bandwidth
144.2GB/s
112.0GB/s
Render Config
Shading Units
960
768
TMUs
80
48
ROPs
24
32
L1 Cache
16 KB (per SMX)
128 KB per Array
L2 Cache
384 KB
1024 KB
Compute Units
—
12
RT Cores
—
12
L3 Cache
—
8 MB
Theoretical Performance
Pixel Rate
20.64 GPixel/s
74.59 GPixel/s
Texture Rate
82.56 GTexel/s
111.9 GTexel/s
FP32 (float)
1.981 TFLOPS
3.580 TFLOPS
FP64 (double)
82.56 GFLOPS
223.8 GFLOPS
FP16 (half)
—
7.161 TFLOPS
Graphics Processor
GPU Name
GK106
Navi 24
GPU Variant
GK106-400-A1
Navi 24 XL-W
Architecture
Kepler
RDNA 2.0
Foundry
TSMC
TSMC
Process Size
28 nm
6 nm
Transistors
2.54 billion
5.4 billion
Die Size
221 mm²
107 mm²
Board Design
TDP
140W
50W
Suggested PSU
300 W
250 W
Outputs
2x DVI1x HDMI 1.4a1x DisplayPort 1.2
2x DisplayPort 1.4a
Power Connectors
1x 6-pin
None
Graphics Features
DirectX
12 (11_0)
12 Ultimate (12_2)
OpenGL
4.6
4.6
OpenCL
3.0
2.2
Vulkan
1.1
1.3
CUDA
3.0
—
Shader Model
5.1
6.6
Benchmark
3DMark Time Spy
1,194
—
3DMark Time Spy Extreme
260
—
OctaneBench
27
—
Blender
111
221
▲ Specs Compare Data sourced from official specifications and benchmark tests.