Home GPU Comparison NVIDIA GeForce GTX 660 Ti vs NVIDIA A40 PCIe

NVIDIA GeForce GTX 660 Ti vs NVIDIA A40 PCIe

We compared two Desktop platform GPUs: 2GB VRAM GeForce GTX 660 Ti and 48GB VRAM A40 PCIe to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.

Main Differences

NVIDIA GeForce GTX 660 Ti 's Advantages
Lower TDP (150W vs 300W)
NVIDIA A40 PCIe 's Advantages
Released 8 years and 2 months late
Boost Clock has increased by 78% (1740MHz vs 980MHz)
More VRAM (48GB vs 2GB)
Larger VRAM bandwidth (695.8GB/s vs 144.2GB/s)
9408 additional rendering cores

Score

Benchmark

FP32 (float)
GeForce GTX 660 Ti
2.634 TFLOPS
A40 PCIe +1320%
37.42 TFLOPS
Blender
GeForce GTX 660 Ti
169
A40 PCIe +2260%
3990

Graphics Card

Aug 2012
Release Date
Oct 2020
GeForce 600
Generation
Tesla
Desktop
Type
Desktop
PCIe 3.0 x16
Bus Interface
PCIe 4.0 x16

Clock Speeds

915 MHz
Base Clock
1305 MHz
980 MHz
Boost Clock
1740 MHz
1502 MHz
Memory Clock
1812 MHz

Memory

2GB
Memory Size
48GB
GDDR5
Memory Type
GDDR6
192bit
Memory Bus
384bit
144.2GB/s
Bandwidth
695.8GB/s

Render Config

-
-
-
-
SM Count
84
1344
Shading Units
10752
112
TMUs
336
24
ROPs
112
-
Tensor Cores
336
-
RT Cores
84
16 KB (per SMX)
L1 Cache
128 KB (per SM)
384 KB
L2 Cache
6 MB
-
-
-

Theoretical Performance

27.44 GPixel/s
Pixel Rate
194.9 GPixel/s
109.8 GTexel/s
Texture Rate
584.6 GTexel/s
-
FP16 (half)
37.42 TFLOPS
2.634 TFLOPS
FP32 (float)
37.42 TFLOPS
109.8 GFLOPS
FP64 (double)
584.6 GFLOPS

Board Design

150W
TDP
300W
450 W
Suggested PSU
700 W
2x DVI 1x HDMI 1.4a 1x DisplayPort 1.2
Outputs
3x DisplayPort 1.4a
2x 6-pin
Power Connectors
8-pin EPS

Graphics Processor

GK104
GPU Name
GA102
GK104-300-KD-A2
GPU Variant
-
Kepler
Architecture
Ampere
TSMC
Foundry
Samsung
28 nm
Process Size
8 nm
3.54 billion
Transistors
28.3 billion
294 mm²
Die Size
628 mm²

Graphics Features

12 (11_0)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.1
Vulkan
1.3
3.0
CUDA
8.6
5.1
Shader Model
6.6
© 2025 - TopCPU.net