NVIDIA GeForce GTX 970 vs NVIDIA GeForce RTX 2080 SUPER

VS

NVIDIA GeForce GTX 970 NVIDIA GeForce RTX 2080 SUPER

We compared two Desktop platform GPUs: 4GB VRAM GeForce GTX 970 and 8GB VRAM GeForce RTX 2080 SUPER to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.

Main Differences

NVIDIA GeForce GTX 970 's Advantages

Lower TDP (148W vs 250W)

NVIDIA GeForce RTX 2080 SUPER 's Advantages

Released 4 years and 10 months late

Boost Clock has increased by 54% (1815MHz vs 1178MHz)

More VRAM (8GB vs 4GB)

Larger VRAM bandwidth (495.9GB/s vs 224.4GB/s)

1408 additional rendering cores

Score

Benchmark

FP32 (float)

GeForce GTX 970

3.92 TFLOPS

GeForce RTX 2080 SUPER +184%

11.15 TFLOPS

3DMark Time Spy

GeForce GTX 970

3625

GeForce RTX 2080 SUPER +218%

11546

Shadow of the Tomb Raider 2160p

GeForce GTX 970

15

GeForce RTX 2080 SUPER +220%

48

Shadow of the Tomb Raider 1440p

GeForce GTX 970

30

GeForce RTX 2080 SUPER +203%

91

Shadow of the Tomb Raider 1080p

GeForce GTX 970

40

GeForce RTX 2080 SUPER +222%

129

GTA 5 2160p

GeForce GTX 970

42

GeForce RTX 2080 SUPER +95%

82

GTA 5 1440p

GeForce GTX 970

44

GeForce RTX 2080 SUPER +168%

118

GTA 5 1080p

GeForce GTX 970

98

GeForce RTX 2080 SUPER +83%

180

GeForce GTX 970

VS

GeForce RTX 2080 SUPER

Graphics Card

Sep 2014

Release Date

Jul 2019

GeForce 900

Generation

GeForce 20

Desktop

Type

Desktop

PCIe 3.0 x16

Bus Interface

PCIe 3.0 x16

Clock Speeds

1050 MHz

Base Clock

1650 MHz

1178 MHz

Boost Clock

1815 MHz

1753 MHz

Memory Clock

1937 MHz

Memory

4GB

Memory Size

8GB

GDDR5

Memory Type

GDDR6

256bit

Memory Bus

256bit

224.4GB/s

Bandwidth

495.9GB/s

Render Config

-

SM Count

48

-

Compute Units

-

1664

Shading Units

3072

104

TMUs

192

56

ROPs

64

-

Tensor Cores

384

-

RT Cores

48

48 KB (per SMM)

L1 Cache

64 KB (per SM)

2 MB

L2 Cache

4 MB

Theoretical Performance

65.97 GPixel/s

Pixel Rate

116.2 GPixel/s

122.5 GTexel/s

Texture Rate

348.5 GTexel/s

-

FP16 (half)

22.30 TFLOPS

3.920 TFLOPS

FP32 (float)

11.15 TFLOPS

122.5 GFLOPS

FP64 (double)

348.5 GFLOPS

Graphics Processor

GM204

GPU Name

TU104

GM204-200-A1

GPU Variant

TU104-450-A1

Maxwell 2.0

Architecture

Turing

TSMC

Foundry

TSMC

28 nm

Process Size

12 nm

5.2 billion

Transistors

13.6 billion

398 mm²

Die Size

545 mm²

Board Design

148W

TDP

250W

300 W

Suggested PSU

600 W

1x DVI 1x HDMI 2.0 3x DisplayPort 1.4a

Outputs

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

2x 6-pin

Power Connectors

1x 6-pin + 1x 8-pin

Graphics Features

12 (12_1)

DirectX

12 Ultimate (12_2)

4.6

OpenGL

4.6

3.0

OpenCL

3.0

1.3

Vulkan

1.3

5.2

CUDA

7.5

6.4

Shader Model

6.6

Related GPU Comparisons

1

NVIDIA GeForce GTX 970 vs NVIDIA GeForce GTX 1050 Ti

2

NVIDIA GeForce GTX 970 vs AMD Radeon RX 6500 XT

3

NVIDIA GeForce GTX 970 vs NVIDIA GeForce GTX 1060 6 GB

4

NVIDIA GeForce GTX 970 vs NVIDIA GeForce RTX 3060

5

NVIDIA GeForce GTX 970 vs NVIDIA GeForce RTX 4060 Ti 8 GB

6

NVIDIA GeForce GTX 970 vs NVIDIA GeForce RTX 4060

7

NVIDIA GeForce GTX 970 vs AMD FirePro W7100

8

NVIDIA GeForce GTX 970 vs NVIDIA GeForce2 Ultra

9

NVIDIA GeForce GTX 970 vs NVIDIA GeForce RTX 4070 AD103

10

NVIDIA GeForce GTX 970 vs AMD Radeon HD 7730

Related News

1

Time to Step Up, AMD and Intel! Nvidia Faces Antitrust Lawsuits in France, US, and EU

2

Intel Arrow Lake-S Features Dual Direct M.2 Slots: One PCIe 5.0 x4 and One PCIe 4.0 x4

3

AMD Ryzen 9000X3D Series to Feature Fully Unlocked Overclocking; DDR5-6400: The 'Sweet Spot' for Zen 5 Memory Speeds

4

Intel Z890 Motherboard Specs Leaked: Farewell to DDR4 Memory

5

AMD Ryzen 9000 Series Now Available for Pre-order in Europe: 9950X Priced at €660, Shipping by August 2

6

AMD's Latest Breakthrough Technology Could Change the Game in the Future

7

Researchers Utilize NVIDIA Omniverse Platform to Analyze and Improve 3D Stacked Chip Designs

8

TSMC to Receive Over 60 EUV Lithography Machines Over the Next Two Years, Investing More Than $12.3 Billion

9

Samsung's Own 3nm Yield is Disheartening: Galaxy S25 May Introduce MediaTek for the First Time

10

AMD Ryzen 9000 DDR5 Memory Frequency Soars: Reaches 8000MHz with All Four Slots Occupied