⋮  

NVIDIA GeForce RTX 3060 Ti Will Be Announced On November 17th

Submit

NVIDIA's upcoming RTX 3060 Ti was confirmed recently with its full specifications getting leaked as well and now it looks like we have a launch date as well. According to MyDrivers.com (via Videocardz), the GA104 based RTX 3060 Ti is going to be launching on the 17th of November. We have also heard the same from our sources (more specifically, this being the embargo lift date) and are therefore not tagging this as a rumor - although Jensen can and probably will move the date around a bit just to mess with the leak scene.

NVIDIA RTX 3060 Ti will be announced on the 17th of November

The NVIDIA GeForce RTX 3060 Ti will feature GA104-200 GPU with 4864 CUDA cores and 8GB of GDDR6 memory clocked at 14 Gbps. The bus width will be 256-bits for a total bandwidth of 448 GB/s of bandwidth. Since the board will require less power, the TBP should be around 200W with the reference design clocking in at around 180W. This is a 5W increase over the RTX 2070 at 175W and in line with how we expect the Samsung node to fair in terms of power efficiency when compared to TSMC's nodes.

Keep in mind that the reason NVIDIA's RTX 3090 and RTX 3080 cards are not scaling linearly in performance is due to bottlenecking by game engines and binaries that are not designed to handle this much amount of cores. We know that the hardware and driver stack scales linearly because of the benchmark performance of these cards in software like vRAY and Octane - which are designed to handle a huge amount of graphics power. This means that as you scale down cores, performance will not scale down linearly. In fact, I fully expect the RTX 3060 Ti to beat the RTX 2080 clock for clock! Assuming slightly less clocks than the RTX 2080 Ti, it should easily trade blows with the former flagship.

The RTX 3060 Ti series of cards has been in the pipeline for a very long time and Videocardz has finally received confirmation of the same.

Here is the full RTX lineup:

NVIDIA GeForce RTX 30 Series 'Ampere' Graphics Card Specifications:

Graphics Card NameNVIDIA GeForce RTX 3050NVIDIA GeForce RTX 3050 TiNVIDIA GeForce RTX 3060NVIDIA GeForce RTX 3060 TiNVIDIA GeForce RTX 3070NVIDIA GeForce RTX 3070 TiNVIDIA GeForce RTX 3080NVIDIA GeForce RTX 3080 TiNVIDIA GeForce RTX 3090
GPU NameAmpere GA107Ampere GA107Ampere GA106-300Ampere GA104-200Ampere GA104-300Ampere GA104-400Ampere GA102-200Ampere GA102-225Ampere GA102-300
Process NodeSamsung 8nmSamsung 8nmSamsung 8nmSamsung 8nmSamsung 8nmSamsung 8nmSamsung 8nmSamsung 8nmSamsung 8nm
Die SizeTBATBATBA395.2mm2395.2mm2395.2mm2628.4mm2628.4mm2628.4mm2
TransistorsTBATBATBA17.4 Billion17.4 Billion17.4 Billion28 Billion28 Billion28 Billion
CUDA Cores2048?2560?358448645888614487041024010496
TMUs / ROPs64 / 4080 / 48112 / 64152 / 80184 / 96192/ 96272 / 96320 / 112328 / 112
Tensor / RT Cores64 / 1680 / 20112 / 28152 / 38184 / 46192/ 48272 / 68320 / 80328 / 82
Base ClockTBATBA1320 MHz1410 MHz1500 MHz1575 MHz1440 MHz1365 MHz1400 MHz
Boost ClockTBATBA1780 MHz1665 MHz1730 MHz1770 MHz1710 MHz1665 MHz1700 MHz
FP32 ComputeTBATBA12.7 TFLOPs16.2 TFLOPs20 TFLOPs22 TFLOPs30 TFLOPs34 TFLOPs36 TFLOPs
RT TFLOPsTBATBA25.4 TFLOPs32.4 TFLOPs40 TFLOPs42 TFLOPs58 TFLOPs67 TFLOPs69 TFLOPs
Tensor-TOPsTBATBA101 TOPs129.6 TOPs163 TOPs174 TOPs238 TOPs273 TOPs285 TOPs
Memory Capacity4 GB GDDR6?4 GB GDDR6?12 GB GDDR68 GB GDDR68 GB GDDR68 GB GDDR6X10 GB GDDR6X12 GB GDDR6X24 GB GDDR6X
Memory Bus128-bit128-bit192-bit256-bit256-bit256-bit320-bit384-bit384-bit
Memory SpeedTBATBA15 Gbps14 Gbps14 Gbps19 Gbps19 Gbps19 Gbps19.5 Gbps
BandwidthTBATBA360 Gbps448 Gbps448 Gbps608 Gbps760 Gbps912 Gbps936 Gbps
TGP~75W~100W170W200W220W290W320W350W350W
Price (MSRP / FE)$149?$199?$329$399 US$499 US$599 US$699 US$1199$1499 US
Launch (Availability)2021?2021?February 2021December 202029th October 202010th June 202117th September 20203rd June 202124th September 2020

AMD just recently launched its Navi 22 series on October 28 and that could be one reason why NVIDIA has decided to launch the Ti-based variant first. With 3080 and 3090 cards still out of stock, gamers are clearly hungry to get their hands on a next-generation GPU. Oh and if you are wondering with what is happening over at NVIDIA then I have some juicy details for you.

See, yields for the initial few batches of the Samsung 8nm node are lower than expected and expensive. The company expects the yields (and therefore prices for wafers) to significantly improve in the coming months. To protect its shareholders, the company has been cautious about its orders of the first few batches and has placed significantly higher volume orders for later batches. This problem was further exacerbated by bots scraping up the entire volume from the get-go. We expect the bulk orders to start hitting before the holiday season (assuming, once again, that miners don't gobble it all up of course).

Submit