In 2013, Nvidia launched the Titan graphics card series, where the products stand out with high price tags and full-scale variants of the world’s fastest graphics chips under the hood. In December 2017, the company unveiled Titan V, which with a price tag of SEK 31,500 for the first time took the graphics architecture Volta to PC users.
On August 20 this year, new graphics cards for consumers were also released, and under the hood of the Geforce RTX 2000 series are Turing-based graphics circuits. Geforce RTX 2080 Ti is the most powerful product from the graphics card trio that was unveiled during the late summer, but now the card looks to face competition from Titan RTX, which is now stuck in the picture.
Ziggy the kitten helping me upgrade my GPU in the kitchen. https://t.co/A3H9epsUIV pic.twitter.com/5T7A8JvBbx
— Gavin Free (@GavinFree) 30 november 2018
Through a post on Twitter shows Gavin Free an image on his computer where an illuminated Titan logo adorns the graphics card, which according to the associated caption has recently been upgraded. The picture also reveals that the graphics card is equipped with the same type of cooler used for Nvidia’s reference cards in the Geforce RTX 2000 series, where the heat sink is accompanied by two axial fans.
In the comments section of the post, the Youtube profile also responds Jayztwocents with a picture on the packaging of the graphics card. The box reveals the name Titan RTX but no details about the amount of graphics memory or other specifications are visible. However, it is not unlikely that the card will be equipped with the graphics circuit TU102, which in a scaled-down version can be seen in the Geforce RTX 2080 Ti. It is worth mentioning that the company-oriented Quadro RTX 8000 uses full-scale TU102, which is flanked by 48 GB of GDDR6 memory.
TU102 houses a total of 72 SM clusters, which means 4,608 CUDA cores, 288 texture units, 576 Tensor cores and 72 RT cores for ray tracing. Geforce RTX 2080 Ti has 68 SM clusters activated and in addition, its memory bus has been scaled down from 384 to 352 bits. Whether Titan RTX uses a variant of the circuit or not is currently unknown, which also applies to price and time of launch.
Specifications: Titanium RTX, Quadro RTX 8000 and Geforce RTX 2000
Titan RTX | RTX 8000 panel | RTX 2080 Ti | RTX 2080 | RTX 2070 | |
---|---|---|---|---|---|
Technical | 12 nm TSMC | 12 nm TSMC | 12 nm TSMC | 12 nm TSMC | 12 nm TSMC |
Circuit | TU102(?) | TU102 | TU102 | TU104 | TU106 |
Circuit surface | 754 mm2 | 754 mm2 | 754 mm2 | 545 mm2 | 445 mm2 |
Transistors | 18.6 billion | 18.6 billion | 18.6 billion | 13.6 billion | 10.6 billion |
Architecture | Turing | Turing | Turing | Turing | Turing |
CUDA cores | ? | 4 608 st. | 4 352 st. | 2 944 st. | 2 304 st. |
Texture units | ? | 288 st. | 272 st. | 184 st. | 144 st. |
Raster units | ? | 96 st. | 88 st. | 64 st. | 64 st. |
Clock frequency | ? | ? | 1 350 MHz | 1 515 MHz | 1 410 MHz |
GPU Boost | ? | ~1 736 MHz | 1 545 MHz | 1 710 MHz | 1 620 MHz |
Memory bus | 384-bit(?) | 384-bit | 352-bit | 256-bit | 256-bit |
Memory amount | 12 GB(?) | 24 / 48 GB GDDR6 | 11 GB GDDR6 | 8 GB GDDR6 | 8 GB GDDR6 |
Memory frequency | 14 000 MHz | 14 000 MHz | 14 000 MHz | 14 000 MHz | 14 000 MHz |
Memory bandwidth | 672 GB/s(?) | 672 GB/s | 616 GB/s | 448 GB/s | 448 GB/s |
Power supply | 8+8-pin(?) | ? | 8+8-pin | 8+6-pin | 8-pin |
TDP | ? | ? | 250 W | 215 W | 175 W |
Rec. Award | ? | ? | 999 USD | 699 USD | 499 USD |
* Values apply to Nvidia’s Founder’s Edition of each model, which comes with 90 MHz overclocking. In addition to slightly higher performance, this in all cases leads to an increase in TDP of 10 W.