The hardware fall 2020 began strongly with the Nvidia Geforce RTX 3000 series “Ampere”, with which the company took graphics performance to new heights. So far, only the top models from RTX 3070 to RTX 3080 and RTX 3090 have been launched, but soon it’s time for the architecture Ampere to climb down in price.
Next in line is the Geforce RTX 3060 Ti, which is expected to be equipped with the same graphics circuit as the RTX 3070, but in a more scaled-down design. Now find what appear to be official performance figures for the upcoming graphics card. In the presentation image, the model is compared to a duo Geforce RTX 2000 from the previous generation – its official predecessor and a top model.
Videocardz, which is responsible for the data, writes that the tests were performed in the resolution 2,560 × 1,440 pixels and that the processor is an Intel Core i9-10900K. The graphs clearly show how the Geforce RTX 3060 Ti runs past its formal predecessor RTX 2060 Super, but also that it beats the former top model RTX 2080 Super by a good margin in both regular screening and ray tracing.
RTX 3070 |
RTX 3060 Ti * |
RTX 2080 Super |
RTX 2060 Super |
|
---|---|---|---|---|
Technical |
8 nm Samsung |
8 nm Samsung |
12 nm TSMC |
12 nm TSMC |
Circuit |
GA104 |
GA104 |
TU104 |
TU106 |
Circuit surface |
392 mm² |
392 mm² |
545 mm² |
445 mm² |
Transistors |
17.4 billion |
17.4 billion |
18.6 billion |
10.6 billion |
Architecture |
Ampere |
Ampere |
Turing |
Turing |
CUDA cores |
5 888 st. |
4 864 st. |
3 072 st. |
2 176 st. |
RT cores |
46 st. |
38 st. |
48 st. |
34 st. |
Tensor cores |
184 st. |
152 st. |
384 st. |
272 st. |
Texture units |
184 st. |
152 st. |
192 st. |
136 st. |
Raster units |
96 st. |
96 st. |
64 st. |
64 st. |
Clock frequency |
1 500 MHz |
1 410 MHz |
1 650 MHz |
1 470 MHz |
GPU Boost |
1 725 MHz |
1 665 MHz |
1 815 MHz |
1 650 MHz |
Computational power |
20 313 GFLOPS |
16 197 GFLOPS |
11 151 GFLOPS |
7 181 GFLOPS |
Memory amount |
8 GB GDDR6 |
8 GB GDDR6 |
8 GB GDDR6 |
8 GB GDDR6 |
Memory frequency |
14 000 MHz |
14 000 MHz |
15 500 MHz |
14 000 MHz |
Memory bus |
256-bit |
256-bit |
256-bit |
256-bit |
Memory bandwidth |
448 GB/s |
448 GB/s |
496 GB/s |
448 GB/s |
Power supply |
12-pin |
12-pin |
8+6-pin |
8-pin |
Outputs |
3 st. DP 1.4a |
3 st. DP 1.4a |
1 st. DL-DVI |
1 st. DL-DVI |
TBP |
220 W |
? |
250 W |
175 W |
Launch price |
499 USD |
? |
699 USD |
399 USD |
* Specifications for Geforce RTX 3060 Ti are based on previous reports
Nvidia Geforce RTX 3060 Ti will be based on the graphics circuit GA104 with 38 of 48 SM clusters activated, which can be compared to 46 for RTX 3070 with the same GA104 circuit. The number of SM clusters gives 4,864 CUDA cores, which are expected to have a base frequency of 1,410 MHz with 1,665 MHz in boost. This is flanked by a 256-bit memory bus with 8 GB GDDR6 at 14,000 MHz for a theoretical bandwidth of 448 GB / s.
The same report states that Nvidia will launch the Geforce RTX 3060 Ti on December 2, 2020, ie two weeks after the AMD Radeon RX 6800 and RX 6800 XT make their debut.
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.