NVIDIA GeForce RTX 4070 vs NVIDIA GeForce RTX 2070 SUPER

VS

NVIDIA GeForce RTX 4070

NVIDIA GeForce RTX 2070 SUPER

We compared two Desktop platform GPUs: 12GB VRAM GeForce RTX 4070 and 8GB VRAM GeForce RTX 2070 SUPER to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.

Main Differences

NVIDIA GeForce RTX 4070 's Advantages

Released 3 years and 9 months late

Boost Clock has increased by 40% (2475MHz vs 1770MHz)

More VRAM (12GB vs 8GB)

Larger VRAM bandwidth (504.2GB/s vs 448.0GB/s)

3328 additional rendering cores

Lower TDP (200W vs 215W)

Score

Benchmark

FP32 (float)

GeForce RTX 4070 +221%

29.15 TFLOPS

GeForce RTX 2070 SUPER

9.062 TFLOPS

3DMark Time Spy

GeForce RTX 4070 +76%

17856

GeForce RTX 2070 SUPER

10095

Shadow of the Tomb Raider 2160p

GeForce RTX 4070 +95%

82

GeForce RTX 2070 SUPER

42

Shadow of the Tomb Raider 1440p

GeForce RTX 4070 +100%

160

GeForce RTX 2070 SUPER

80

Shadow of the Tomb Raider 1080p

GeForce RTX 4070 +116%

256

GeForce RTX 2070 SUPER

118

Cyberpunk 2077 2160p

GeForce RTX 4070 +50%

54

GeForce RTX 2070 SUPER

36

Cyberpunk 2077 1440p

GeForce RTX 4070 +116%

93

GeForce RTX 2070 SUPER

43

Cyberpunk 2077 1080p

GeForce RTX 4070 +106%

130

GeForce RTX 2070 SUPER

63

Battlefield 5 2160p

GeForce RTX 4070 +75%

98

GeForce RTX 2070 SUPER

56

Battlefield 5 1440p

GeForce RTX 4070 +70%

172

GeForce RTX 2070 SUPER

101

Battlefield 5 1080p

GeForce RTX 4070 +50%

200

GeForce RTX 2070 SUPER

133

GTA 5 2160p

GeForce RTX 4070 +94%

132

GeForce RTX 2070 SUPER

68

GTA 5 1440p

GeForce RTX 4070 +50%

144

GeForce RTX 2070 SUPER

96

GTA 5 1080p

GeForce RTX 4070 +5%

190

GeForce RTX 2070 SUPER

180

GeForce RTX 4070

VS

GeForce RTX 2070 SUPER

Graphics Card

Apr 2023

Release Date

Jul 2019

GeForce 40

Generation

GeForce 20

Desktop

Type

Desktop

PCIe 4.0 x16

Bus Interface

PCIe 3.0 x16

Clock Speeds

1920 MHz

Base Clock

1605 MHz

2475 MHz

Boost Clock

1770 MHz

1313 MHz

Memory Clock

1750 MHz

Memory

12GB

Memory Size

8GB

GDDR6X

Memory Type

GDDR6

192bit

Memory Bus

256bit

504.2GB/s

Bandwidth

448.0GB/s

Render Config

-

46

SM Count

40

5888

Shading Units

2560

184

TMUs

160

64

ROPs

64

184

Tensor Cores

320

46

RT Cores

40

128 KB (per SM)

L1 Cache

64 KB (per SM)

36 MB

L2 Cache

4 MB

-

Theoretical Performance

158.4 GPixel/s

Pixel Rate

113.3 GPixel/s

455.4 GTexel/s

Texture Rate

283.2 GTexel/s

29.15 TFLOPS

FP16 (half)

18.12 TFLOPS

29.15 TFLOPS

FP32 (float)

9.062 TFLOPS

455.4 GFLOPS

FP64 (double)

283.2 GFLOPS

Board Design

200W

TDP

215W

550 W

Suggested PSU

550 W

1x HDMI 2.1 3x DisplayPort 1.4a

Outputs

1x HDMI 2.0 3x DisplayPort 1.4a 1x USB Type-C

1x 16-pin

Power Connectors

1x 6-pin + 1x 8-pin

Graphics Processor

AD104

GPU Name

TU104

AD104-250-A1

GPU Variant

TU104-410-A1

Ada Lovelace

Architecture

Turing

TSMC

Foundry

TSMC

5 nm

Process Size

12 nm

35.8 billion

Transistors

13.6 billion

295 mm²

Die Size

545 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

6.7

Shader Model

6.6

Related GPU Comparisons

1

NVIDIA GeForce RTX 4070 vs AMD Radeon RX 6400

2

NVIDIA GeForce RTX 4070 vs NVIDIA GeForce GTX 1070 Ti

3

NVIDIA GeForce RTX 4070 vs AMD Radeon HD 6970

4

NVIDIA GeForce RTX 4070 vs AMD Radeon PRO V710

5

NVIDIA GeForce RTX 4070 vs ATI Radeon HD 5670

6

NVIDIA GeForce RTX 4070 vs NVIDIA P106 100

7

NVIDIA GeForce RTX 4070 vs NVIDIA GeForce GT 430

8

NVIDIA GeForce RTX 4070 vs NVIDIA GeForce 8400 GS Rev. 2

9

NVIDIA GeForce RTX 4070 vs NVIDIA RTX 4000 Ada Generation

10

NVIDIA GeForce RTX 4070 vs AMD Radeon Pro WX 2100

Related News

1

The Commencement of ARM and Qualcomm Licensing Dispute Trial: Potential Major Impact on PC Market

2

NVIDIA Allegedly Equips RTX 5080 with 30Gbps Memory Speed, Other Models to Feature 28Gbps

3

Intel Reports High Return Rates for Devices Featuring Snapdragon X Series; Qualcomm Counters with 'Industry Standard' Claim

4

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

5

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

6

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

7

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

8

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

9

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

10

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