NVIDIA GeForce RTX 3060 vs NVIDIA GeForce RTX 2070

VS

NVIDIA GeForce RTX 3060 NVIDIA GeForce RTX 2070

We compared two Desktop platform GPUs: 12GB VRAM GeForce RTX 3060 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 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)

NVIDIA GeForce RTX 2070 's Advantages

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

Score

Benchmark

FP32 (float)

GeForce RTX 3060 +70%

12.74 TFLOPS

GeForce RTX 2070

7.465 TFLOPS

3DMark Time Spy

GeForce RTX 3060

8767

GeForce RTX 2070 +1%

8863

Shadow of the Tomb Raider 2160p

GeForce RTX 3060 +18%

44

GeForce RTX 2070

37

Shadow of the Tomb Raider 1440p

GeForce RTX 3060 +17%

80

GeForce RTX 2070

68

Shadow of the Tomb Raider 1080p

GeForce RTX 3060 +18%

116

GeForce RTX 2070

98

Cyberpunk 2077 2160p

GeForce RTX 3060

30

GeForce RTX 2070 +6%

32

Cyberpunk 2077 1440p

GeForce RTX 3060

36

GeForce RTX 2070 +2%

37

Cyberpunk 2077 1080p

GeForce RTX 3060 +1%

56

GeForce RTX 2070

55

Battlefield 5 2160p

GeForce RTX 3060 +1%

55

GeForce RTX 2070

54

Battlefield 5 1440p

GeForce RTX 3060 +5%

101

GeForce RTX 2070

96

Battlefield 5 1080p

GeForce RTX 3060 +10%

142

GeForce RTX 2070

128

GTA 5 2160p

GeForce RTX 3060

50

GeForce RTX 2070 +72%

86

GTA 5 1440p

GeForce RTX 3060

82

GeForce RTX 2070 +9%

90

GTA 5 1080p

GeForce RTX 3060

133

GeForce RTX 2070 +33%

178

GeForce RTX 3060

VS

GeForce RTX 2070

Graphics Card

Jan 2021

Release Date

Oct 2018

GeForce 30

Generation

GeForce 20

Desktop

Type

Desktop

PCIe 4.0 x16

Bus Interface

PCIe 3.0 x16

Clock Speeds

1320 MHz

Base Clock

1410 MHz

1777 MHz

Boost Clock

1620 MHz

1875 MHz

Memory Clock

1750 MHz

Memory

12GB

Memory Size

8GB

GDDR6

Memory Type

GDDR6

192bit

Memory Bus

256bit

360.0GB/s

Bandwidth

448.0GB/s

Render Config

28

SM Count

36

-

Compute Units

-

3584

Shading Units

2304

112

TMUs

144

48

ROPs

64

112

Tensor Cores

288

28

RT Cores

36

128 KB (per SM)

L1 Cache

64 KB (per SM)

3 MB

L2 Cache

4 MB

Theoretical Performance

85.30 GPixel/s

Pixel Rate

103.7 GPixel/s

199.0 GTexel/s

Texture Rate

233.3 GTexel/s

12.74 TFLOPS

FP16 (half)

14.93 TFLOPS

12.74 TFLOPS

FP32 (float)

7.465 TFLOPS

199.0 GFLOPS

FP64 (double)

233.3 GFLOPS

Graphics Processor

GA106

GPU Name

TU106

GA106-300-A1

GPU Variant

TU106-400A-A1

Ampere

Architecture

Turing

Samsung

Foundry

TSMC

8 nm

Process Size

12 nm

12 billion

Transistors

10.8 billion

276 mm²

Die Size

445 mm²

Board Design

170W

TDP

175W

450 W

Suggested PSU

450 W

1x HDMI 2.1 3x DisplayPort 1.4a

Outputs

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

1x 12-pin

Power Connectors

1x 8-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

8.6

CUDA

7.5

6.6

Shader Model

6.6

Related GPU Comparisons

1

NVIDIA GeForce RTX 3060 vs NVIDIA GeForce RTX 4050

2

NVIDIA GeForce RTX 3060 vs NVIDIA T1000 8 GB

3

NVIDIA GeForce RTX 3060 vs NVIDIA GeForce RTX 2080

4

NVIDIA GeForce RTX 3060 vs NVIDIA GeForce RTX 2070 SUPER

5

NVIDIA GeForce RTX 3060 vs NVIDIA GeForce RTX 3050 OEM

6

NVIDIA GeForce RTX 3060 vs NVIDIA GeForce GTX 1060 6 GB

7

NVIDIA GeForce RTX 3060 vs NVIDIA GeForce RTX 4060 Ti 16 GB

8

NVIDIA GeForce RTX 3060 vs AMD FirePro D300

9

NVIDIA GeForce RTX 3060 vs NVIDIA GeForce GTX 960 OEM

10

NVIDIA GeForce RTX 3060 vs Intel Arc A310

Related News

1

NVIDIA to Ramp Up Orders and Add New Suppliers to Meet Explosive Demand for Blackwell Products

2

NVIDIA Informs Brands of Reduced Supply for RTX 40 Series GPUs

3

Only 3 Weeks Left! AMD Zen5 Launching Soon

4

Ilya Departs OpenAI to Launch New Company Aiming at Superintelligence!

5

Comprehensive Overview of AMD Ryzen 9000 Zen5 Desktop CPUs

6

Intel May Increase Base Frequencies for Arrow Lake-S / H / HX, High-End Chips to Reach 3GHz or Higher

7

It's 2024: This Company Released a Laptop Supporting DOS and Windows 95

8

AMD's Strix Halo Supports Up to 128GB Memory, Clearly Designed for AI Large Language Models

9

AMD to Launch Advanced Ryzen AI PRO Series Soon

10

Intel Delays Lunar Lake Shipment: Postponed from June to September