Notebookcheck Logo

NVIDIA launches Titan RTX

The NVIDIA Titan RTX GPU. (Source: NVIDIA)
The NVIDIA Titan RTX GPU. (Source: NVIDIA)
The latest ray trace-supporting and Turing-powered card, the Titan RTX, was launched at today's (December 3, 2018) Conference on Neural Information Processing Systems. With its 24GB in GDDR6 memory, 576 multi-precision Tensor Cores and 72 RT Cores, it is clearly aimed at deep-learning professionals.

NVIDIA has debuted its newest and possibly most powerful GPU, the Titan RTX, today. It may be the most elaborately-spec'd card to feature the Turing architecture yet. Despite earlier speculation, the Titan RTX packs 24GB of GDDR6 memory rather than 12. This memory has a bandwidth of 672 gigabytes per second (GBps). It also features 72 Turing RT Cores and 576 multi-precision Turing Tensor Cores.

These properties are rated to deliver up to 130 teraflops (TFLOPs) in deep-learning power and 11 GigaRays in terms of ray-tracing performance. The Titan RTX is also equipped with a 100GBps NVIDIA NVLink, in case a user wants to scale up with more than one of these cards. This card also has VirtualLink for next-generation virtual reality applications.

NVIDIA asserts that this new card is "the world’s most powerful desktop GPU". It is clearly directed at professionals in the arenas of AI, data science and content creation. All of the Titan RTX's professional attributes also commands a professional pricetag: it is to be made available in Europe and the US for US$2,499 later in December.

Source(s)

static version load dynamic
Loading Comments
Comment on this article
Please share our article, every link counts!
Deirdre O Donnell, 2018-12- 3 (Update: 2018-12- 3)