NVIDIA GeForce RTX 3070 Ti 16 GB

This is a GPU manufactured with Samsung 8nm process, based on Nvidia Ampere architecture. It features 17.4 billion transistors, 6144 CUDA cores and 16GB GDDR6X memory, with 4MB L2 cache, theoretical performance of 21.75TFLOPS, with total power consumption of 290W.

Graphics Card

[Report Issues]

Release Date

Unknown

Generation

GeForce 30

Type

Desktop

Bus Interface

PCIe 4.0 x16

Clock Speeds

[Report Issues]

Base Clock

1575 MHz

Boost Clock

1770 MHz

Memory Clock

1188 MHz

Memory

[Report Issues]

Memory Size

16GB

Memory Type

GDDR6X

Memory Bus

256bit

Bandwidth

608.3GB/s

Render Config

[Report Issues]

SM Count

48

Shading Units

6144

TMUs

192

ROPs

96

Tensor Cores

192

RT Cores

48

L1 Cache

128 KB (per SM)

L2 Cache

4 MB

Theoretical Performance

[Report Issues]

Pixel Rate

169.9 GPixel/s

Texture Rate

339.8 GTexel/s

FP16 (half)

21.75 TFLOPS

FP32 (float)

21.75 TFLOPS

FP64 (double)

339.8 GFLOPS

Graphics Processor

[Report Issues]

GPU Name

GA104

GPU Variant

GA104-401-A1

Architecture

Ampere

Foundry

Samsung

Process Size

8 nm

Transistors

17.4 billion

Die Size

392 mm²

Board Design

[Report Issues]

TDP

290W

Suggested PSU

600 W

Outputs

1x HDMI 2.1
3x DisplayPort 1.4a

Power Connectors

1x 12-pin

Graphics Features

[Report Issues]

DirectX

12 Ultimate (12_2)

OpenGL

4.6

OpenCL

3.0

Vulkan

1.3

CUDA

8.6

Shader Model

6.6

Rankings

[Report Issues]

FP32 (float)

AMD Radeon Pro W6900X 32 GB GDDR6

22.02 TFLOPS

NVIDIA CMP 90HX 10 GB GDDR6X

21.89 TFLOPS

NVIDIA GeForce RTX 3070 Ti 16 GB 16 GB GDDR6X

21.75 TFLOPS

NVIDIA GeForce RTX 3070 Ti GA102 8 GB GDDR6X

21.75 TFLOPS

NVIDIA GeForce RTX 3070 Ti 8 GB GDDR6X

21.75 TFLOPS

NVIDIA GeForce RTX 3070 Ti 8 GB GA102 8 GB GDDR6X

21.75 TFLOPS

AMD Radeon RX 7600 8 GB GDDR6

21.75 TFLOPS

Blender

NVIDIA RTX A5500 24 GB GDDR6

4316

NVIDIA A40 PCIe 48 GB GDDR6

4170

NVIDIA GeForce RTX 3070 Ti 16 GB 16 GB GDDR6X

4092

NVIDIA GeForce RTX 4070 Mobile 8 GB GDDR6

3963

NVIDIA RTX A4500 Embedded 16 GB GDDR6

3920

AMD Radeon RX 7900 XT 20 GB GDDR6

3905

NVIDIA L40 48 GB GDDR6

3901

OctaneBench

Intel Arc Pro A40 6 GB GDDR6

411

NVIDIA GeForce RTX 3080 Mobile 8 GB GDDR6

407

NVIDIA GeForce RTX 3070 Ti 16 GB 16 GB GDDR6X

397

NVIDIA RTX A5500 Mobile 16 GB GDDR6

389

NVIDIA GeForce RTX 4070 Mobile 8 GB GDDR6

370

NVIDIA GeForce RTX 3060 Ti GA103 8 GB GDDR6

365

NVIDIA Tesla V100S PCIe 32 GB 32 GB HBM2

365

Related Comparisons

1

Intel Arc A770 vs NVIDIA GeForce RTX 3070 Ti 16 GB

2

NVIDIA GeForce RTX 3070 Ti 16 GB vs Intel Arc B580

3

NVIDIA GeForce RTX 5060 vs NVIDIA GeForce RTX 3070 Ti 16 GB

4

NVIDIA A100 PCIe vs NVIDIA GeForce RTX 3070 Ti 16 GB

5

NVIDIA RTX 2000 Ada Generation vs NVIDIA GeForce RTX 3070 Ti 16 GB

6

NVIDIA GeForce RTX 3090 vs NVIDIA GeForce RTX 3070 Ti 16 GB

7

NVIDIA GeForce RTX 4070 Ti vs NVIDIA GeForce RTX 3070 Ti 16 GB

8

NVIDIA GeForce RTX 3070 Ti 16 GB vs 3dfx Voodoo4-2 4200 PCI 16 MB

9

NVIDIA GeForce RTX 3070 Ti 16 GB vs AMD Radeon R9 380X

10

NVIDIA GeForce RTX 3070 Ti 16 GB vs AMD Radeon Pro 5500 XT

Related News

1

Intel Finally Achieves Frame Generation! 'F1 24' Becomes the First XeSS 2 Game

2

World's First! Intel Arc B580 Graphics Card Arrives Early

3

AMD RX 8800 XT's Ray Tracing Performance Surges by 45%, Rivals RTX 4080 with 25% Power Reduction!

4

AMD Set to Unveil RDNA 4 Architecture at CES 2025, At Least One Radeon RX 8000 Series Launch Expected in January

5

RTX 50 Desktop Edition Exclusively Uses Samsung GDDR7 Memory! The Other Two Giants Focus on Laptops

6

External GPU Performance Test: AMD RX 7800M Shows 28% Higher Efficiency with OCuLink Compared to USB4 Interface

7

New Intel Arc A310 Mini Card: Four HDMI Ports in a Row

8

Intel Isn't Giving Up on Discrete Graphics Cards! The Third Generation Is Really Coming

9

The RTX 50 Series Upgrades to 12V-2x6 Power Connectors Across the Board! Maximum Power of 450W

10

AMD's Most Powerful Integrated GPU with 40 Units Gets a Name! Radeon 8060S/8050S vs. Mobile RTX 4070 Showdown?