NVIDIA GeForce RTX 3090 Ti vs NVIDIA TITAN X Pascal

VS

NVIDIA GeForce RTX 3090 Ti NVIDIA TITAN X Pascal

We compared two Desktop platform GPUs: 24GB VRAM GeForce RTX 3090 Ti and 12GB VRAM TITAN X Pascal to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.

Main Differences

NVIDIA GeForce RTX 3090 Ti 's Advantages

Released 5 years and 5 months late

Boost Clock has increased by 21% (1860MHz vs 1531MHz)

More VRAM (24GB vs 12GB)

Larger VRAM bandwidth (1008GB/s vs 480.4GB/s)

7168 additional rendering cores

NVIDIA TITAN X Pascal 's Advantages

Lower TDP (250W vs 450W)

Score

Benchmark

FP32 (float)

GeForce RTX 3090 Ti +264%

40 TFLOPS

TITAN X Pascal

10.97 TFLOPS

3DMark Time Spy

GeForce RTX 3090 Ti +131%

22082

TITAN X Pascal

9531

Shadow of the Tomb Raider 2160p

GeForce RTX 3090 Ti +150%

105

TITAN X Pascal

42

Shadow of the Tomb Raider 1440p

GeForce RTX 3090 Ti +114%

167

TITAN X Pascal

78

Shadow of the Tomb Raider 1080p

GeForce RTX 3090 Ti +64%

210

TITAN X Pascal

128

GTA 5 2160p

GeForce RTX 3090 Ti +45%

143

TITAN X Pascal

98

GTA 5 1440p

GeForce RTX 3090 Ti +79%

187

TITAN X Pascal

104

GTA 5 1080p

GeForce RTX 3090 Ti +20%

226

TITAN X Pascal

188

GeForce RTX 3090 Ti

VS

TITAN X Pascal

Graphics Card

Jan 2022

Release Date

Aug 2016

GeForce 30

Generation

GeForce 10

Desktop

Type

Desktop

PCIe 4.0 x16

Bus Interface

PCIe 3.0 x16

Clock Speeds

1560 MHz

Base Clock

1417 MHz

1860 MHz

Boost Clock

1531 MHz

1313 MHz

Memory Clock

1251 MHz

Memory

24GB

Memory Size

12GB

GDDR6X

Memory Type

GDDR5X

384bit

Memory Bus

384bit

1008GB/s

Bandwidth

480.4GB/s

Render Config

84

SM Count

28

-

Compute Units

-

10752

Shading Units

3584

336

TMUs

224

112

ROPs

96

336

Tensor Cores

-

84

RT Cores

-

128 KB (per SM)

L1 Cache

48 KB (per SM)

6 MB

L2 Cache

3 MB

Theoretical Performance

208.3 GPixel/s

Pixel Rate

147.0 GPixel/s

625.0 GTexel/s

Texture Rate

342.9 GTexel/s

40.00 TFLOPS

FP16 (half)

171.5 GFLOPS

40.00 TFLOPS

FP32 (float)

10.97 TFLOPS

625.0 GFLOPS

FP64 (double)

342.9 GFLOPS

Graphics Processor

GA102

GPU Name

GP102

GA102-350-A1

GPU Variant

GP102-400-A1

Ampere

Architecture

Pascal

Samsung

Foundry

TSMC

8 nm

Process Size

16 nm

28.3 billion

Transistors

11.8 billion

628 mm²

Die Size

471 mm²

Board Design

450W

TDP

250W

850 W

Suggested PSU

600 W

1x HDMI 2.1 3x DisplayPort 1.4a

Outputs

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

1x 16-pin

Power Connectors

1x 6-pin + 1x 8-pin

Graphics Features

12 Ultimate (12_2)

DirectX

12 (12_1)

4.6

OpenGL

4.6

3.0

OpenCL

3.0

1.3

Vulkan

1.3

8.6

CUDA

6.1

6.6

Shader Model

6.4

Related GPU Comparisons

1

NVIDIA GeForce RTX 3090 Ti vs NVIDIA A10 PCIe

2

NVIDIA GeForce RTX 3090 Ti vs NVIDIA A100 PCIe

3

NVIDIA GeForce RTX 3090 Ti vs NVIDIA Tesla P100 PCIe 16 GB

4

NVIDIA GeForce RTX 3090 Ti vs NVIDIA GeForce RTX 4060 Ti

5

NVIDIA GeForce RTX 3090 Ti vs NVIDIA GeForce RTX 4070

6

NVIDIA GeForce RTX 3090 Ti vs NVIDIA GeForce RTX 4080

7

NVIDIA NVS 1000 vs NVIDIA GeForce RTX 3090 Ti

8

NVIDIA GeForce RTX 3090 Ti vs NVIDIA GeForce GTX 950 OEM

9

NVIDIA GeForce RTX 3090 Ti vs NVIDIA GeForce GTX 1060 3 GB

10

NVIDIA GeForce RTX 3090 Ti vs NVIDIA GeForce GTX 1080 Ti

Related News

1

Changes in Intel Arrow Lake P/E Core Layout: Two Major Benefits

2

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

3

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

4

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

5

Intel Z890 Motherboard Specs Leaked: Farewell to DDR4 Memory

6

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

7

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

8

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

9

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

10

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