NVIDIA GeForce RTX 2070 vs NVIDIA GeForce RTX 3060

VS

NVIDIA GeForce RTX 2070 NVIDIA GeForce RTX 3060

We compared two Desktop platform GPUs: 8GB VRAM GeForce RTX 2070 and 12GB VRAM GeForce RTX 3060 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.

Main Differences

NVIDIA GeForce RTX 2070's Advantages

Larger VRAM bandwidth (448.0GB/s vs 360.0GB/s)

NVIDIA GeForce RTX 3060's Advantages

Released 2 years and 3 months late

Boost Clock has increased by 10% (1777MHz vs 1620MHz)

More VRAM (12GB vs 8GB)

1280 additional rendering cores

Lower TDP (170W vs 175W)

Score

Benchmark

FP32 (float)

GeForce RTX 2070

7.465 TFLOPS

GeForce RTX 3060 +70%

12.74 TFLOPS

3DMark Time Spy

GeForce RTX 2070 +1%

8875

GeForce RTX 3060

8755

Shadow of the Tomb Raider 2160p

GeForce RTX 2070

37

GeForce RTX 3060 +18%

44

Shadow of the Tomb Raider 1440p

GeForce RTX 2070

68

GeForce RTX 3060 +17%

80

Shadow of the Tomb Raider 1080p

GeForce RTX 2070

98

GeForce RTX 3060 +18%

116

Cyberpunk 2077 2160p

GeForce RTX 2070 +6%

32

GeForce RTX 3060

30

Cyberpunk 2077 1440p

GeForce RTX 2070 +2%

37

GeForce RTX 3060

36

Cyberpunk 2077 1080p

GeForce RTX 2070

55

GeForce RTX 3060 +1%

56

Battlefield 5 2160p

GeForce RTX 2070

54

GeForce RTX 3060 +1%

55

Battlefield 5 1440p

GeForce RTX 2070

96

GeForce RTX 3060 +5%

101

Battlefield 5 1080p

GeForce RTX 2070

128

GeForce RTX 3060 +10%

142

GTA 5 2160p

GeForce RTX 2070 +72%

86

GeForce RTX 3060

50

GTA 5 1440p

GeForce RTX 2070 +9%

90

GeForce RTX 3060

82

GTA 5 1080p

GeForce RTX 2070 +33%

178

GeForce RTX 3060

133

GeForce RTX 2070

VS

GeForce RTX 3060

Graphics Card

Oct 2018

Release Date

Jan 2021

GeForce 20

Generation

GeForce 30

Desktop

Type

Desktop

PCIe 3.0 x16

Bus Interface

PCIe 4.0 x16

Clock Speeds

1410MHz

Base Clock

1320MHz

1620MHz

Boost Clock

1777MHz

1750MHz

Memory Clock

1875MHz

Memory

8GB

Memory Size

12GB

GDDR6

Memory Type

GDDR6

256bit

Memory Bus

192bit

448.0 GB/s

Bandwidth

360.0 GB/s

Render Config

36

SM Count

28

-

Compute Units

-

2304

Shading Units

3584

144

TMUs

112

64

ROPs

48

288

Tensor Cores

112

36

RT Cores

28

64 KB (per SM)

L1 Cache

128 KB (per SM)

4MB

L2 Cache

3MB

Theoretical Performance

103.7 GPixel/s

Pixel Rate

85.30 GPixel/s

233.3 GTexel/s

Texture Rate

199.0 GTexel/s

14.93 TFLOPS

FP16 (half)

12.74 TFLOPS

7.465 TFLOPS

FP32 (float)

12.74 TFLOPS

233.3 GFLOPS

FP64 (double)

199.0 GFLOPS

Graphics Processor

TU106

GPU Name

GA106

TU106-400A-A1

GPU Variant

GA106-300-A1

Turing

Architecture

Ampere

TSMC

Foundry

Samsung

12 nm

Process Size

8 nm

10,800 million

Transistors

12,000 million

445mm²

Die Size

276mm²

Board Design

175W

TDP

170W

450W

Suggested PSU

450W

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

Outputs

1x HDMI 2.1 3x DisplayPort 1.4a

1x 8-pin

Power Connectors

1x 12-pin

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

7.5

CUDA

8.6

6.6

Shader Model

6.6

Related GPU Comparisons

1

NVIDIA GeForce RTX 2070 vs NVIDIA GeForce RTX 4060

2

NVIDIA GeForce GTX 1660 SUPER vs NVIDIA GeForce RTX 2070

3

NVIDIA GeForce RTX 3050 8 GB vs NVIDIA GeForce RTX 2070

4

NVIDIA GeForce RTX 2070 vs AMD Radeon RX 6600

5

NVIDIA GeForce RTX 2060 vs NVIDIA GeForce RTX 2070

6

NVIDIA GeForce RTX 4050 vs NVIDIA GeForce RTX 2070

7

NVIDIA GeForce RTX 3060 vs NVIDIA GeForce RTX 4050

8

NVIDIA GeForce RTX 2070 vs NVIDIA CMP 40HX

9

NVIDIA GeForce RTX 2070 vs AMD Radeon RX Vega Nano

10

NVIDIA GeForce RTX 2070 vs NVIDIA RTX 3500 Embedded Ada Generation