GeForce RTX 20 series
First consumer GPUs with hardware-enabled real-time ray tracing.
The GeForce RTX 20 series is a lineup of graphics cards from Nvidia, built on the company's Turing microarchitecture. These were the first consumer GPUs in the industry to support real-time ray tracing through dedicated hardware. Shipping began on September 20, 2018, and a higher-spec "Super" line was announced on July 2, 2019. Unlike previous Nvidia launches, this series skipped the entry-level market, which was instead covered by the GeForce GTX 16 series. The RTX 20 series was succeeded by the GeForce RTX 30 series, based on the Ampere architecture, which debuted in 2020.
Nvidia teased the first card, the RTX 2080, on August 14, 2018, after introducing the Turing architecture at SIGGRAPH. The full series was officially announced at Gamescom on August 20, 2018, marketed as the first graphics cards designed for real-time ray tracing, thanks to dedicated tensor and RT cores. The company had trademarked the names GeForce RTX and Quadro RTX earlier that month.
The RTX 2080 launched as the successor to the GeForce 10 series, with Nvidia claiming it was up to 75% faster than the GTX 1080 in certain games. PC Gamer described it as the most significant generational upgrade since the first CUDA cores in 2006. Factory-overclocked versions, including a "Ti" edition, appeared later in 2018. The Founders Edition cards came overclocked by default with a three-year warranty. TechRadar called the RTX 2080 Ti the most powerful GPU on the market at the time. While the RTX 2080 Founders Edition received positive performance reviews from PC Gamer in September 2018, it was criticized for its high price and the limited availability of ray tracing content. In January 2019, Tom's Hardware called the RTX 2080 Ti Xtreme the fastest gaming card available, though it noted issues with noise, size, and heat. Nvidia also claimed in August 2018 that these cards were the first to feature GDDR6 memory, DisplayPort 1.4 supporting 8K HDR at 60Hz, and a USB Type-C output for next-generation VR headsets.
Supply of the RTX 2080 Ti was described as "extremely tight" in October 2018, following earlier delays. By November, MSI offered nine different RTX 2080-based cards. The Titan RTX, released in December 2018, was priced at $2,500, significantly more than the $1,300 RTX 2080 Ti.
In January 2019, Nvidia announced that RTX cards would appear in 40 new laptops.
Quick Facts
- Date
- 2018-09-20 · 2019-07-09 (Super refresh)
- Discontinued
- 2022-11-28
- Manufacturer
- TSMC
- Designfirm
- Nvidia
- Codename
- TU10x
- Architecture
- Turing · Ampere (only RTX 2050 Mobile)
- Model
- GeForce RTX series
- Fab
- TSMC 12 nm (FinFET)
- Entry
- GeForce RTX 2050 (Laptop only) / GeForce RTX 2060 / GeForce RTX 2060 (12 GB)
- Midrange
- GeForce RTX 2060 Super
- Highend
- GeForce RTX 2070 · GeForce RTX 2070 Super · GeForce RTX 2080 · GeForce RTX 2080 Super
Facts from the source article.
Lore & Background
On August 14, 2018, Nvidia teased the announcement of the first card in the 20 series, the GeForce RTX 2080, shortly after introducing the Turing architecture at SIGGRAPH earlier that year. The GeForce RTX 20 series was finally announced at Gamescom on August 20, 2018, becoming the first line of graphics cards 'designed to handle real-time ray tracing' thanks to the 'inclusion of dedicated tensor and RT cores.' In August 2018, it was reported that Nvidia had trademarked GeForce RTX and Quadro RTX as names. The line started shipping on September 20, 2018, serving as the successor to the GeForce 10 series. Released in late 2018, the RTX 2080 was marketed as up to 75% faster than the GTX 1080 in various games. After the initial release, factory overclocked versions were released in late 2018, including the 'Ti' edition, while Founders Edition cards were overclocked by default and had a three-year warranty. In October 2018, supply of the 2080 Ti was reported as 'extremely tight' after availability had already been delayed. By November 2018, MSI was offering nine different RTX 2080-based graphics cards. Released in December 2018, the line's Titan RTX was initially priced at $2500.
Reader's Guide
The GeForce RTX 20 series introduced real-time hardware ray tracing to consumer graphics, a technology that had been in development at Nvidia for 10 years. The ray tracing performed by the RT cores can be used to produce effects such as reflections, refractions, shadows, depth of field, light scattering and caustics, replacing traditional raster techniques such as cube maps and depth maps. Instead of replacing rasterization entirely, ray tracing is offered in a hybrid model, in which the information gathered from ray tracing can be used to augment the rasterized shading. The second generation Tensor Cores work in cooperation with the RT cores, used mainly for de-noising partially ray traced images and for DLSS (deep learning super-sampling), a method to replace anti-aliasing by artificially generating detail to upscale the rendered image. Due to production problems surrounding the RTX 30-series cards and a general shortage of graphics cards caused by the COVID-19 pandemic and increased cryptocurrency mining, the RTX 2060 and its Super counterpart, alongside the GTX 1050 Ti, were brought back into production in 2021. Furthermore, the RTX 2060 was reissued on December 7, 2021 as a variant with 12GB of VRAM.
Did You Know?
- The RTX 20 series was the first line of graphics cards designed to handle real-time ray tracing in a consumer product.
- Nvidia switched from Micron to Samsung GDDR6 memory chips by November 2018 due to reported faults with launch models.
- The Titan RTX was initially priced at $2500, significantly more than the $1300 then needed for a GeForce RTX 2080 Ti.
More in Nvidia and AMD Graphics Processors 1-24
Spotted an error? Know more?
Reader corrections go straight into our review queue. Suggest an edit · How this site is sourced