Nvidia will soon launch Geforce GTX 1650 and a possible GTX 1650 Ti, which are believed to round out the Turing graphics family. When Nvidia was in full swing launching its then new flagships in the RTX series during the autumn, Gigabyte published a campaign for an RTX 2070 Ti, which the company stated was a typo.
Six months later, whether or not the graphics card is still an open question. The Userbenchmark database contains what looks like a new graphics card from Nvidia. Of particular interest is the fact that it ranks between the Geforce RTX 2070 and the RTX 2080 in terms of performance, which has caused speculation about the RTX 2070 Ti to flare up again.
Something that stands out is the odd amount of memory 7.5 GB, which is 0.5 GB or 512 MB lower than both RTX 2080 and RTX 2070. Considering that there are no GDDR6 memory circuits with a capacity lower than 1 GB, it is possibly if an error reading in the software.
RTX 2080 Ti |
RTX 2080 |
RTX 2070 Ti |
RTX 2070 |
|
---|---|---|---|---|
Technical |
12 nm TSMC |
12 nm TSMC |
12 nm TSMC |
12 nm TSMC |
Circuit |
TU102 |
TU104 |
TU104 |
TU106 |
Circuit surface |
754 mm2 |
545 mm2 |
545 mm2 |
445 mm2 |
Transistors |
18.6 billion |
13.6 billion |
13.6 billion |
10.6 billion |
Architecture |
Turing |
Turing |
Turing |
Turing |
CUDA cores |
4 352 st. |
2 944 st. |
? |
2 304 st. |
Texture units |
272 st. |
184 st. |
? |
144 st. |
Raster units |
88 st. |
64 st. |
64 st. |
64 st. |
Clock frequency |
1 350 MHz |
1 515 MHz |
? |
1 410 MHz |
GPU Boost |
1 545 MHz |
1 710 MHz |
? |
1 620 MHz |
Computational power |
13 448 GFLOPS |
10 068 GFLOPS |
? |
7 465 GFLOPS |
Memory bus |
352-bit |
256-bit |
256-bit |
256-bit |
Memory amount |
11 GB GDDR6 |
8 GB GDDR6 |
8 GB GDDR6 |
8 GB GDDR6 |
Memory frequency |
14 000 MHz |
14 000 MHz |
14 000 MHz |
14 000 MHz |
Memory bandwidth |
616 GB/s |
448 GB/s |
448 GB/s |
448 GB/s |
Power supply |
8+8-pin |
8+6-pin |
? |
8-pin |
SLI connection |
NVLink 2.0 x16 |
NVLink 2.0 x8 |
NVLink 2.0 x8(?) |
– |
Outputs |
1 st. HDMI 2.0b |
1 st. HDMI 2.0b |
1 st. HDMI 2.0b |
1 st. HDMI 2.0b |
TDP |
250 W |
215 W |
? |
175 W |
SweClockers |
159 |
134 |
? |
108 |
Rec. Award |
999 USD |
699 USD |
599 USD(?) |
499 USD |
* Values apply to Nvidia’s Founders 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.
Assuming that Nvidia has a Geforce RTX 2070 Ti in the pipeline, it is highly likely that it is the graphics circuit TU104, which lays the foundation for RTX 2080. This is because RTX 2070 is already delivered with TU106 in its full-scale design, which makes it difficult for Nvidia to deliver a higher performing graphics card with that circuit.
Common to the Geforce RTX 2080 and RTX 2070 are memory bus, GDDR6 memory capacity and speed. It is therefore reasonable that a possible RTX 2070 Ti follows this to the letter, with 8 GB GDDR6 with an effective clock frequency of 14,000 MHz and bandwidth 448 GB / s.
Another interesting aspect is that the TU104 graphics circuit, unlike the TU106 used in the Geforce RTX 2070, has built-in support for the NVLink 2.0 interface. It would thus be possible for an RTX 2070 Ti to receive SLI support, with the caveat that Nvidia can also choose to deactivate the function.
Nvidia has Geforce RTX 2070 and RTX 2080 have recommended prices of 499 and 699 USD respectively, while the performance advantage for the latter is about 20 percent. It is therefore possible that an RTX 2070 Ti would place itself in the middle of the duo in terms of price. In Sweden, that would mean around SEK 7,000.
Why Nvidia would like to launch a graphics card between Geforce RTX 2070 and RTX 2080 is spelled AMD. At the beginning of February, the company launched Radeon VII, which on average places itself between the duo, and during the year, the Navi architecture will be launched at 7 nanometers. Another probable reason is that Nvidia has accumulated large stocks of TU104 that do not qualify for use in RTX 2080.
Finally, Guru3D writes that the graphics card ID number is more reminiscent of a Quadro than Geforce, which in such cases would mean that it is an upcoming graphics card placed between Quadro RTX 5000 and RTX 4000. However, this does not rule out that Nvidia uses a similar configuration for a future graphics card in the Geforce game segment.
Does Nvidia have a Geforce RTX 2070 Ti coming? In such cases, such a graphics card is needed in the market and would you consider buying one? Discuss!
Mining on RTX 3070. Overclocking, tuning, profitability, consumption: If you are interested in finding more…
Mining with GTX 1660, 1660 Ti, 1660 Super. Overclocking, settings, consumption, profitability, comparisons - If…
Mining with RTX 2070 and 2070 Super. Overclocking, profitability, consumption, comparison What the RTX 2070…
Mining with RTX 3060, 3060 Ti. Limitations, overclocking, settings, consumption, profitability, comparison Let's look at…
Alphacool Eisblock Aurora Acryl GPX-A (2022) with Sapphire Radeon RX 6950 XT Nitro+ Pure in…
In the ever-evolving landscape of business strategy, Bitcoin has emerged as a pivotal asset. With…
This website uses cookies.