Nvidia GeForce RTX 3090 Ti Specs

Nvidia GeForce RTX 3090 Ti on Amazon USA

Specifications of the Nvidia GeForce RTX 3090 Ti graphics card dedicated to the desktop sector, with 10752 shading units, its maximum frequency is 1.9GHz The table below makes it possible to observe well the lithography, the number of transistors (if present), the offered cache memory, the quantity of texture mapping units, of render output units, the release date, the GFLOPS performance, the values obtained in the benchmark platforms.


Graphics card Nvidia GeForce RTX 3090 Ti
Market (main) Desktop
Release date Q1 2022
Model number GA102-350-A1
GPU name GA102
Architecture Ampere
Generation GeForce 30
Lithography 8 nm
Transistors 28,300,000,000
Bus interface PCIe 4.0 x16
GPU base clock 1.56 GHz
GPU boost clock 1.86 GHz
Memory frequency 1,313 MHz
Effective memory speed 21 GB/s
Memory size 24 GB
Memory type GDDR6X
Memory bus 384 bit
Memory bandwidth 1,008 GB/s
TDP 450 W
Suggested PSU 900W ATX Power Supply
Multicard technology 2-way NVLink

3x DisplayPort
Cores (compute units, SM, SMX) 84
Shading units (cuda cores) 10,752
TMUs 336
ROPs 112
Tensor cores 336
RT cores 84
Cache memory 6 MB
Pixel fillrate 208.3 GPixel/s
Texture fillrate 625.0 GTexel/s
Performance FP16 (half) 40.0 TFLOPS
Performance FP32 (float) 40.0 TFLOPS
Performance FP64 (double) 625 GFLOPS
Tensor FLOPS 320T
Ray-tracing performance 79.9 TFLOPS

Price: For technical reasons, we cannot currently display a price less than 24 hours, or a real-time price. This is why we prefer for the moment not to show a price. You should refer to the respective online stores for the latest price, as well as availability.

TMUs: texture mapping units. This unit was a physical processor separated from the main graphics processing units. It is able to distort a bitmap image, and also to resize it, to rotate it and to place it as a texture onto a plane of a specific 3D model.

ROPs: render output units. The other name of this unit is raster operations pipeline. This hadware component is taking pixel and texel information, and processing it through vector and matrix operations. The result will be a depth value or a final pixel. It is able to control antialiasing with the merge of several sample into one pixel.

SM: streaming multiprocessor. These processors are implied in the Kepler's power efficiency when the GPU is using one unified clock speed.

Performances :

Performance comparison between this graphics card and those of equivalent power, for this we consider the results generated on benchmark softwares and rendering performances.

Pixel fillrate performance comparison for this graphics card:

Pixel fillrate performance in GPixels/s
Nvidia A100 PCIe 225.6
AMD Radeon Pro Vega II Duo 220.2
Intel Arctic Sound 2T 216
Nvidia GeForce RTX 3090 Ti 208.3
Nvidia Quadro GV100 208.3
Asus ROG STRIX RTX 3090 Gaming OC 208.3
AMD Radeon RX 6800 202.1
Nvidia RTX A6000 201.6
MSI GeForce RTX 3090 Gaming X Trio 199.9
Nvidia GeForce RTX 3090 189.8

The term pixel fillrate is refering to the number of pixels that the video card is able to generate every second. This performance is achieved by multiplying the raster output units (ROPs) by the clock frequency of the graphics processor unit (GPU).

Texture fillrate performance comparison for this graphics card:

Texture fillrate performance in GTexels/s
AMD Radeon RX 6950 XT 743.7
AMD Radeon RX 6900 XT 720
AMD Radeon Pro W6900X 688
AMD Radeon RX 6800 XT 648
Nvidia GeForce RTX 4070 630.8
Nvidia GeForce RTX 3090 Ti 625
Asus ROG STRIX RTX 3090 Gaming OC 610.1
Nvidia A100 PCIe 609.1
Nvidia RTX A6000 604.8
MSI GeForce RTX 3090 Gaming X Trio 585.5

The term texture fillrate refers to the number of map texture elements (texels) that the GPU is capable of generating per second. This performance is achieved by multiplying the texture mapping units (TMUs) by the clock frequency of the graphics processor unit.

FP32 performance comparison (single precision; float; floating-point 32) for this graphics card:

FP32 Performance in GFLOPS
Nvidia GeForce RTX 4090 67,020
Nvidia GeForce RTX 4080 Ti 64,510
Nvidia GeForce RTX 4080 58,430
Nvidia GeForce RTX 4070 40,370
Nvidia GeForce RTX 3090 Ti 40,000
Asus ROG STRIX RTX 3090 Gaming OC 39,050
Nvidia RTX A6000 38,710
MSI GeForce RTX 3090 Gaming X Trio 37,470
Nvidia GeForce RTX 3090 35,580

Single precision floating point format, also known as FP32, is a computer number format that typically occupies 32 bits in PC memory. This represents a wide dynamic range of numeric values that employs a floating point.

List of comparisons:

AMDAMD RadeonAMD Radeon GraphicsAMD Radeon HD 8000AMD Radeon R2AMD Radeon R5AMD Radeon R6AMD Radeon R7AMD Radeon R7 200AMD Radeon R9AMD Radeon RXAMD Radeon RX 300AMD Radeon RX 400AMD Radeon RX 500AMD Radeon RX 5000AMD Radeon RX 5000 MobileAMD Radeon RX 6000AMD Radeon RX 6000 MobileAMD Radeon RX VegaAMD Radeon VegaAMD Radeon Vega 11AMD Radeon Vega 3AMD Radeon Vega 6AMD Radeon Vega 8AMD Radeon Vega MobileAppleARMARM MaliARM Mali-400ARM Mali-450ARM Mali-470ARM Mali-G31ARM Mali-G51ARM Mali-G52ARM Mali-G57ARM Mali-G610ARM Mali-G68ARM Mali-G71ARM Mali-G710ARM Mali-G72ARM Mali-G76ARM Mali-G77ARM Mali-G78ARM Mali-T720ARM Mali-T760ARM Mali-T764ARM Mali-T820ARM Mali-T830ARM Mali-T860ARM Mali-T880AsusATIBroadcomBroadcom VideoCoreDMPGainwardGigabyteImaginationImagination PowerVRImagination PowerVR SGX543Imagination PowerVR SGX544IntelIntel ArcIntel Arctic SoundIntel HD GraphicsIntel Iris GraphicsIntel Iris Plus GraphicsIntel Iris Xe Graphics G7Intel Iris Xe Graphics MobileIntel UHD GraphicsIntel UHD Graphics 610Intel UHD Graphics 620Intel UHD Graphics 630Intel UHD Graphics 730Intel Xe GraphicsMSINvidiaNvidia GeForceNvidia GeForce 1000Nvidia GeForce 1000 MobileNvidia GeForce 1600Nvidia GeForce 1600 MobileNvidia GeForce 2000Nvidia GeForce 2000 MobileNvidia GeForce 3000Nvidia GeForce 3000 MobileNvidia GeForce 4000Nvidia GeForce 500Nvidia GeForce 600Nvidia GeForce 600MNvidia GeForce 700Nvidia GeForce 700MNvidia GeForce 800M seriesNvidia GeForce 900Nvidia GeForce 900MNvidia GeForce GTNvidia GeForce GTXNvidia GeForce MXNvidia GeForce RTXNvidia GM20BNvidia Quadro seriesNvidia TeslaNvidia VoltaQualcommQualcomm AdrenoSamsungSapphireVivanteXFXZotacGraphics cards groups

List of benchmarks:

FP32 performance


Nvidia GeForce RTX 3090 Ti AMD equivalent

GadgetVersus.com © 2022 - Information - XML sitemap - Privacy policy - Advertising policy - Contact


When you click on links to various merchants on this site and make a purchase, this can result in this site earning a commission. Affiliate programs and affiliations include, but are not limited to, the eBay Partner Network.

As an Amazon Associate I earn from qualifying purchases.

This page includes affiliate links for which the administrator of GadgetVersus may earn a commission at no extra cost to you should you make a purchase. These links are indicated using the hashtag #ad.


We do not assume any responsibility for the data displayed on our website. Please use at your own risk. Some or all of this data may be out of date or incomplete, please refer to the technical page on the respective manufacturer's website to find the latest up-to-date information regarding the specifics of these products.

Trading System Forex W3Ask W3Ask Brasil W3Ask Deutschland W3Ask España W3Ask France W3Ask Italia W3Ask Nederland