Nvidia New RTX 2070, 2080 and 2018 TI Graphics Cards

Nvidia New RTX 2070, 2080 and 2018 TI Graphics Cards

Nvidia’s new high-end graphics cards are the GeForce RTX 2070, RTX 2080 and RTX 2080 Ti, the company announced today during a pre-Gamescom 2018 livestream from Cologne, Germany.




These new 20-series cards will succeed Nvidia’s current top-of-the-line GPUs, the GeForce GTX 1070, GTX 1080 and GTX 1080 Ti. While the company usually waits to launch the more powerful Ti version of a GPU, this time around, it’s releasing the RTX 2080 and RTX 2080 Ti at once.

They won’t come cheap. The Nvidia-manufactured Founders Edition versions will cost $599 for the RTX 2070, $799 for the RTX 2080 and $1,199 for the RTX 2080 Ti. The latter two cards are expected to ship “on or around” Sept. 20, while there is no estimated release date for the RTX 2070. Pre-orders are currently available for the RTX 2080 and 2080 Ti.

Nvidia CEO Jensen Huang announced different “starting at” prices during the keynote presentation. Huang’s presentation said the RTX 2070 will start at $499, the RTX 2080 at $699 and the RTX 2080 Ti at $999. Asked for clarification, an Nvidia representative told Polygon that these amounts reflect retail prices for third-party manufacturers’ cards.

You can see the base specifications for the three graphics cards below.


Spec
RTX 2070 FE
RTX 2070
GTX 1070
GPU architecture
Turing
Turing
Pascal
Boost clock
1710 MHz (OC)
1620 MHz
1683 MHz
Frame buffer
8 GB GDDR6
8 GB GDDR6
8 GB GDDR5
Memory speed
14 Gbps
14 Gbps
8 Gbps

Spec
RTX 2080 FE
RTX 2080
GTX 1080
GPU architecture
Turing
Turing
Pascal
Boost clock
1800 MHz (OC)
1710 MHz
1733 MHz
Frame buffer
8 GB GDDR6
8 GB GDDR6
8 GB GDDR5X
Memory speed
14 Gbps
14 Gbps
10 Gbps

Spec
RTX 2080 Ti FE
RTX 2080 Ti
GTX 1080 Ti
GPU architecture
Turing
Turing
Pascal
Boost clock
1635 MHz (OC)
1545 MHz
1582 MHz
Frame buffer
11 GB GDDR6
11 GB GDDR6
11 GB GDDR5X
Memory speed
14 Gbps
14 Gbps
11 Gbps


The RTX 2070, 2080 and 2080 Ti will be the first consumer-level graphics cards based on Nvidia’s next-generation Turing architecture, which the company announced earlier this month at the SIGGRAPH computing conference. At that time, Nvidia also revealed its first Turing-based products: three GPUs in the company’s Quadro line, which is geared toward professional applications.

All three of the new RTX cards will feature built-in support for real-time ray tracing, a rendering and lighting technique for photorealistic graphics that gaming companies are starting to introduce this year. Nvidia announced a real-time ray tracing technology that it refers to as Nvidia RTX — hence the new naming scheme for the company’s upcoming GPUs — during the 2018 Game Developers Conference in March. Ray tracing is the standard for applications such as visual effects in the film industry, but it is extremely computationally intensive, which has meant that — at least until now — it has been impractical for gaming. In addition to real-time ray tracing, Nvidia’s RTX platform incorporates two existing technologies, programmable shaders and artificial intelligence.

A few game makers also appeared on stage to show off Windows PC games launching in the next six months or so that will support Nvidia RTX. EA DICE showed new footage of Battlefield 5 with RTX-based reflections; 4A Games showed RTX-based lighting in Metro Exodus; and Eidos Montreal showed RTX-based shadows in Shadow of the Tomb Raider.






Comments