NVIDIA GeForce RTX 2060 SUPER vs NVIDIA GeForce RTX 3090 Ti

Table of Contents

Graphics Processor

GPU model TU106 GA102
GPU variant TU106-410-A1 GA102-350-A1
Architecture Turing Ampere
Foundry TSMC Samsung
Manufacturing process 12 nm 8 nm
Number of transistors 10,800 million 28,300 million
Die size 445 mm² 628 mm²

Graphics Card

Release date Jul 9th, 2019 Unknown
Generation GeForce 20 GeForce 30
Predecessor GeForce 10 GeForce 20
Production Active Unreleased
Launch price 399 USD 1,699 USD
Interface PCIe 3.0 x16 PCIe 4.0 x16
Reviews 40 in our database 55 in our database
Successor GeForce 30
gpu.details.availability 2022

Clocks

Base clock 1470 MHz 1560 MHz
Boost clock 1650 MHz 1860 MHz
Memory clock 1750 MHz 14 Gbps effective 1325 MHz 21.2 Gbps effective

Memory Configuration

Memory size 8 GB 24 GB
Memory type GDDR6 GDDR6X
Memory bus width 256 bit 384 bit
Bandwidth 448.0 GB/s 1,018 GB/s

Render Configuration

Shading units 2176 10752
TMUs 136 336
ROPs 64 112
SM count 34 84
Tensor cores 272 336
RT cores 34 84
Cache L1 64 KB (per SM) 128 KB (per SM)
Cache L2 4 MB 6 MB

Performance

Pixel rate 105.6 GPixel/s 208.3 GPixel/s
Texture rate 224.4 GTexel/s 625.0 GTexel/s
FP16 (half) performance 14.36 TFLOPS (2:1) 40.00 TFLOPS (1:1)
FP32 (float) performance 7.181 TFLOPS 40.00 TFLOPS
FP64 (double) performance 224.4 GFLOPS (1:32) 625.0 GFLOPS (1:64)

Dimensions & Outputs

Slot width Dual-slot Triple-slot
Length 229 mm 9 inches 336 mm 13.2 inches
Width 113 mm 4.4 inches 140 mm 5.5 inches
Height 35 mm 1.4 inches 61 mm 2.4 inches
TDP 175 W 450 W
Suggested PSU 450 W 850 W
Outputs 1x DVI1x HDMI2x DisplayPort1x USB Type-C 1x HDMI3x DisplayPort
Power connectors 1x 8-pin 1x 12-pin
Board number PG160 SKU 65 PG132 SKU

API Support & Features

DirectX 12 Ultimate (12_2) 12 Ultimate (12_2)
OpenGL 4.6 4.6
OpenCL 3.0 3.0
Vulkan 1.2 1.2
CUDA 7.5 8.6
Shader model 6.6 6.6

Other Features

Compare

Sysrqmts browser extension icon
Stop overpaying for PC games!
See cheapest prices in Steam store with our browser extension.