NVIDIA GeForce RTX 4090 vs NVIDIA GeForce RTX 2070

VS

NVIDIA GeForce RTX 4090

NVIDIA GeForce RTX 2070

We compared two Desktop platform GPUs: 24GB VRAM GeForce RTX 4090 and 8GB VRAM GeForce RTX 2070 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.

Main Differences

NVIDIA GeForce RTX 4090 's Advantages

Released 3 years and 11 months late

Boost Clock has increased by 56% (2520MHz vs 1620MHz)

More VRAM (24GB vs 8GB)

Larger VRAM bandwidth (1.01TB/s vs 448.0GB/s)

14080 additional rendering cores

NVIDIA GeForce RTX 2070 's Advantages

Lower TDP (175W vs 450W)

Score

Benchmark

FP32 (float)

GeForce RTX 4090 +1006%

82.58 TFLOPS

GeForce RTX 2070

7.465 TFLOPS

3DMark Time Spy

GeForce RTX 4090 +311%

36499

GeForce RTX 2070

8861

Shadow of the Tomb Raider 2160p

GeForce RTX 4090 +400%

185

GeForce RTX 2070

37

Shadow of the Tomb Raider 1440p

GeForce RTX 4090 +311%

280

GeForce RTX 2070

68

Shadow of the Tomb Raider 1080p

GeForce RTX 4090 +210%

304

GeForce RTX 2070

98

Cyberpunk 2077 2160p

GeForce RTX 4090 +193%

94

GeForce RTX 2070

32

Cyberpunk 2077 1440p

GeForce RTX 4090 +400%

185

GeForce RTX 2070

37

Cyberpunk 2077 1080p

GeForce RTX 4090 +254%

195

GeForce RTX 2070

55

Battlefield 5 2160p

GeForce RTX 4090 +244%

186

GeForce RTX 2070

54

Battlefield 5 1440p

GeForce RTX 4090 +111%

203

GeForce RTX 2070

96

Battlefield 5 1080p

GeForce RTX 4090 +66%

213

GeForce RTX 2070

128

GTA 5 2160p

GeForce RTX 4090 +91%

165

GeForce RTX 2070

86

GTA 5 1440p

GeForce RTX 4090 +105%

185

GeForce RTX 2070

90

GTA 5 1080p

GeForce RTX 4090 +4%

186

GeForce RTX 2070

178

GeForce RTX 4090

VS

GeForce RTX 2070

Graphics Card

Sep 2022

Release Date

Oct 2018

GeForce 40

Generation

GeForce 20

Desktop

Type

Desktop

PCIe 4.0 x16

Bus Interface

PCIe 3.0 x16

Clock Speeds

2235 MHz

Base Clock

1410 MHz

2520 MHz

Boost Clock

1620 MHz

1313 MHz

Memory Clock

1750 MHz

Memory

24GB

Memory Size

8GB

GDDR6X

Memory Type

GDDR6

384bit

Memory Bus

256bit

1.01TB/s

Bandwidth

448.0GB/s

Render Config

-

128

SM Count

36

16384

Shading Units

2304

512

TMUs

144

176

ROPs

64

512

Tensor Cores

288

128

RT Cores

36

128 KB (per SM)

L1 Cache

64 KB (per SM)

72 MB

L2 Cache

4 MB

-

Theoretical Performance

443.5 GPixel/s

Pixel Rate

103.7 GPixel/s

1290 GTexel/s

Texture Rate

233.3 GTexel/s

82.58 TFLOPS

FP16 (half)

14.93 TFLOPS

82.58 TFLOPS

FP32 (float)

7.465 TFLOPS

1290 GFLOPS

FP64 (double)

233.3 GFLOPS

Board Design

450W

TDP

175W

850 W

Suggested PSU

450 W

1x HDMI 2.13x DisplayPort 1.4a

Outputs

1x DVI 1x HDMI 2.0 2x DisplayPort 1.4a 1x USB Type-C

1x 16-pin

Power Connectors

1x 8-pin

Graphics Processor

AD102

GPU Name

TU106

AD102-300-A1

GPU Variant

TU106-400A-A1

Ada Lovelace

Architecture

Turing

TSMC

Foundry

TSMC

5 nm

Process Size

12 nm

76.3 billion

Transistors

10.8 billion

609 mm²

Die Size

445 mm²

Graphics Features

12 Ultimate (12_2)

DirectX

12 Ultimate (12_2)

4.6

OpenGL

4.6

3.0

OpenCL

3.0

1.3

Vulkan

1.3

8.9

CUDA

7.5

6.8

Shader Model

6.6

Related GPU Comparisons

1

NVIDIA GeForce RTX 4090 vs AMD Radeon HD 7450 OEM

2

NVIDIA GeForce RTX 4090 vs NVIDIA GeForce GT 610 PCIe x1

3

NVIDIA GeForce RTX 4090 vs NVIDIA GeForce GTX 760 X2

4

NVIDIA GeForce RTX 4090 vs NVIDIA GeForce GT 720 OEM

5

NVIDIA GeForce RTX 4090 vs ATI Radeon HD 2400 PRO PCI

6

NVIDIA GeForce RTX 4090 vs AMD Radeon Pro 5700

7

NVIDIA GeForce RTX 4090 vs ATI Radeon HD 4350

8

NVIDIA GeForce RTX 4090 vs AMD Radeon R7 240

9

NVIDIA GeForce RTX 4090 vs NVIDIA GeForce RTX 4090 D

10

NVIDIA GeForce RTX 4090 vs ATI Radeon HD 5850

Related News

1

Intel Confirms Panther Lake Adopts 18A Process, ES0 Samples Already Sent to Customers

2

Complete Lineup of Core Ultra 200HX/H/U and Core 200H/U Revealed: 31 Models to Dazzle the Eyes

3

Amechi Unveils V1 Mini PC: Only 0.33L Volume with 150W Power Consumption

4

iPhone 17 Series Set for Major Design Overhaul: Camera Module Transformed into Sleek Strip

5

The Thinnest iPhone Ever! iPhone 17 Air Reportedly Enters Foxconn's NPI Stage

6

Apple Allegedly Cancels M4 Extreme, Originally Planned for Mac Pro with 64-Core CPU and 160-Core GPU

7

Cyberpunk 2077 Update 2.2: Intel Arrow Lake Gaming Performance Soars by 33%!

8

Intel Finally Achieves Frame Generation! 'F1 24' Becomes the First XeSS 2 Game

9

World's First! Intel Arc B580 Graphics Card Arrives Early

10

Linux Creator Criticizes AMD and Intel's x86 Microarchitecture: A Complete Disaster