NVIDIA GeForce GTX 660 Ti vs NVIDIA GeForce RTX 4070 SUPER

VS

NVIDIA GeForce GTX 660 Ti NVIDIA GeForce RTX 4070 SUPER

We compared two Desktop platform GPUs: 2GB VRAM GeForce GTX 660 Ti and 12GB VRAM GeForce RTX 4070 SUPER 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 220W)

NVIDIA GeForce RTX 4070 SUPER 's Advantages

Released 11 years and 5 months late

Boost Clock has increased by 153% (2475MHz vs 980MHz)

More VRAM (12GB vs 2GB)

Larger VRAM bandwidth (504.2GB/s vs 144.2GB/s)

5824 additional rendering cores

Score

Benchmark

FP32 (float)

GeForce GTX 660 Ti

2.634 TFLOPS

GeForce RTX 4070 SUPER +1247%

35.48 TFLOPS

3DMark Time Spy

GeForce GTX 660 Ti

1627

GeForce RTX 4070 SUPER +1192%

21021

Blender

GeForce GTX 660 Ti

138

GeForce RTX 4070 SUPER +5100%

7177

OctaneBench

GeForce GTX 660 Ti

21

GeForce RTX 4070 SUPER +3223%

698

GeForce GTX 660 Ti

VS

GeForce RTX 4070 SUPER

Graphics Card

Aug 2012

Release Date

Jan 2024

GeForce 600

Generation

GeForce 40

Desktop

Type

Desktop

PCIe 3.0 x16

Bus Interface

PCIe 4.0 x16

Clock Speeds

915 MHz

Base Clock

1980 MHz

980 MHz

Boost Clock

2475 MHz

1502 MHz

Memory Clock

1313 MHz

Memory

2GB

Memory Size

12GB

GDDR5

Memory Type

GDDR6X

192bit

Memory Bus

192bit

144.2GB/s

Bandwidth

504.2GB/s

Render Config

-

SM Count

56

-

Compute Units

-

1344

Shading Units

7168

112

TMUs

224

24

ROPs

80

-

Tensor Cores

224

-

RT Cores

56

16 KB (per SMX)

L1 Cache

128 KB (per SM)

384 KB

L2 Cache

48 MB

Theoretical Performance

27.44 GPixel/s

Pixel Rate

198.0 GPixel/s

109.8 GTexel/s

Texture Rate

554.4 GTexel/s

-

FP16 (half)

35.48 TFLOPS

2.634 TFLOPS

FP32 (float)

35.48 TFLOPS

109.8 GFLOPS

FP64 (double)

554.4 GFLOPS

Graphics Processor

GK104

GPU Name

AD104

GK104-300-KD-A2

GPU Variant

AD104-350-A1

Kepler

Architecture

Ada Lovelace

TSMC

Foundry

TSMC

28 nm

Process Size

5 nm

3.54 billion

Transistors

35.8 billion

294 mm²

Die Size

294 mm²

Board Design

150W

TDP

220W

450 W

Suggested PSU

550 W

2x DVI 1x HDMI 1.4a 1x DisplayPort 1.2

Outputs

1x HDMI 2.1 3x DisplayPort 1.4a

2x 6-pin

Power Connectors

1x 16-pin

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

8.9

5.1

Shader Model

6.7

Related GPU Comparisons

1

NVIDIA GeForce GTX 660 Ti vs NVIDIA GeForce GTX 460 v2 ES

2

NVIDIA GeForce GTX 750 Ti vs NVIDIA GeForce GTX 660 Ti

3

NVIDIA GeForce GTX 660 Ti vs NVIDIA GeForce GTX 770

4

AMD Radeon R7 250 vs NVIDIA GeForce GTX 660 Ti

5

NVIDIA GeForce GTX 660 Ti vs NVIDIA GeForce 9300 GS Rev. 2

6

NVIDIA GeForce GTX 1050 Ti vs NVIDIA GeForce GTX 660 Ti

7

NVIDIA NVS 1000 vs NVIDIA GeForce GTX 660 Ti

8

NVIDIA GeForce GTX 660 Ti vs AMD Radeon RX 5500 OEM

9

NVIDIA GeForce GTX 660 Ti vs NVIDIA GeForce GTX 950 OEM

10

NVIDIA GeForce GTX 660 Ti vs AMD FirePro D700

Related News

1

Snapdragon 8 Gen 4 to Feature Frame Interpolation for GPU: A Game-Changing Experience

2

Intel Adds 5 New Device IDs to Latest Linux Xe Kernel in Preparation for Battlemage

3

Ryzen AI 9 365 Benchmark Results Leaked: Significant Improvements in Multi-Core and IPC Performance Over Previous Generation

4

Concerns Raised by Unstable 13th/14th Gen Core CPUs: Motherboard Manufacturers Worry About Impact on Arrow Lake Release and Sales

5

Do You Really Know What a "Rendering Engine" Is? Read This Article to Understand All About It

6

New AMD Zen5 Ryzen 9000 Motherboards X870E/X870 to Adopt USB4! But You’ll Have to Wait Two More Months

7

Surpassing RTX 2050! Intel's Next-Gen Integrated Graphics Benchmark Closely Approaches AMD

8

New Benchmarks for AMD Ryzen AI 9 HX 370 Revealed: Single-Core Parity with R9 7945HX3D, Multi-Core Still Lower

9

X3D Performance Beyond Words! AMD Ryzen 7 9700X May Unlock Power Consumption: From 65W to 120W

10

First Benchmark Leak of Intel Core Ultra 7 268V: Single-Core Performance Soars by 20%, Still Lags Behind AMD