ASUS has confirmed two upcoming NVIDIA GeForce RTX 30 series graphics cards, the GeForce RTX 3080 Ti & the GeForce RTX 3060. Both of these graphics cards are scheduled for launch in early ’21 but ASUS has already listed them under their supports and services page.

ASUS GeForce RTX 3080 Ti 20 GB & GeForce RTX 3060 12 GB ROG STRIX Custom Graphics Cards Confirmed

Both graphics cards were spotted by HXL (@9550pro) within ASUS’s support and services page for graphics cards. The list includes the GeForce RTX 30 series ROG STRIX variants and also mentions the unreleased GeForce RTX 3080 Ti & GeForce RTX 3060 graphics cards which we talked about in previous leaks.

The leak confirms that ASUS is working on both overclocked and non-overclocked variants for their ROG STRIX series. The GeForce RTX 3080 Ti will feature 20 GB of GDDR6X memory and the GeForce RTX 3060 will come equipped with 12 GB of GDDR6 memory. Since both of these cards are custom variants, they will be making use of the brand new ROG STRIX cooling solution that we have seen on the existing GeForce RTX 30 ROG STRIX lineup si expect top of the line cooling performance and a beefy custom PCB design.

Details from Kopite7kimi suggest that the GeForce RTX 3080 Ti FE (Founders Edition) graphics card will feature the PG133-SKU15 PCB design and the GA102-250-KD-A1 graphics core. The GA102-250 GPU has also changed since the last time we saw them and is now exactly the same as the GeForce RTX 3090 at 10496 FP32 CUDA cores.

GeForce RTX 3080 Ti 20 GB
GeForce RTX 3080 Ti 20 GB

As for memory, the card will feature 20 GB of GDDR6X memory. Unlike the 19.5 Gbps speeds of the RTX 3090, the GeForce RTX 3080 Ti is said to retain the same memory speeds as the RTX 3080 at 19 Gbps. Since we are getting a 20 GB bus interface, NVIDIA will be using a 320-bit bus interface which equals a total bandwidth of 760 GB/s. TGP for the card is set to be the same as the RTX 3080 at 320 Watts. That’s definitely needed to feed the extra cores so NVIDIA might have to optimize the clocks a bit here.

NVIDIA could undercut the AMD Radeon RX 6900 XT which is a $999 US graphics card with the RTX 3080 Ti though we have to see just how much of a difference the Ti variant makes as it will end up being sandwiched between the RTX 3080 and RTX 3090. There are reports that the RTX 3080 Ti may end up faster than the RTX 3090 due to its higher clock speeds while the RTX 3090 could remain a Titan class product serving the enthusiast and content creation market with its higher VRAM buffer.

The GeForce RTX 3060 is suggested to feature the GA106-400 GPU which is expected to feature 3840 FP32 cores in a total of 30 SM units. The graphics card will make use of the PG190 SKU by board partners which are both GA104 and GA106 pin-compatible. The graphics card has seen a range of memory specs update starting with 6 GB (14 Gbps) and now listed at 12 GB (16 Gbps).

GeForce RTX 3060

It is rumored that the card will feature a massive 12 GB memory buffer which is larger than that of the RTX 3060 Ti, RTX 3070, and even the RTX 3080. This is not confirmed yet but the reason could be that NVIDIA wants to really tackle AMD in the mainstream segment. Again, we saw rumors of 20 GB and 16 GB for the RTX 3080 & RTX 3070 too which didn’t end up being true as they were early designs that were later on canceled.

The card will feature a 192-bit bus interface and at 16 Gbps, delivering bandwidth of up to 384 GB/s. The GeForce RTX 3060 could end up being priced at $299 US which will make it a formidable graphics card.

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 Ti?NVIDIA GeForce RTX 3080NVIDIA GeForce RTX 3080 Ti?NVIDIA GeForce RTX 3090
GPU NameAmpere GA107Ampere GA106?Ampere GA106?Ampere GA104-200Ampere GA104-300Ampere GA102-150Ampere GA102-200Ampere GA102-250Ampere GA102-300
Process NodeSamsung 8nmSamsung 8nmSamsung 8nmSamsung 8nmSamsung 8nmSamsung 8nmSamsung 8nmSamsung 8nmSamsung 8nm
Die SizeTBATBATBA395.2mm2395.2mm2628.4mm2628.4mm2628.4mm2628.4mm2
TransistorsTBATBATBA17.4 Billion17.4 Billion28 Billion28 Billion28 Billion28 Billion
CUDA Cores23043584384048645888742487041049610496
TMUs / ROPsTBATBATBA152 / 80184 / 96232 / 80272 / 96328 / 112328 / 112
Tensor / RT CoresTBATBATBA152 / 38184 / 46232 / 58272 / 68328 / 82328 / 82
Base ClockTBATBATBA1410 MHz1500 MHzTBA1440 MHzTBA1400 MHz
Boost ClockTBATBATBA1665 MHz1730 MHzTBA1710 MHzTBA1700 MHz
FP32 ComputeTBATBATBA16.2 TFLOPs20 TFLOPsTBA30 TFLOPsTBA36 TFLOPs
RT TFLOPsTBATBATBA32.4 TFLOPs40 TFLOPsTBA58 TFLOPsTBA69 TFLOPs
Tensor-TOPsTBATBATBATBA163 TOPsTBA238 TOPsTBA285 TOPs
Memory Capacity4 GB GDDR6?6 GB GDDR6?6 GB GDDR6?8 GB GDDR68 GB GDDR610 GB GDDR6X?10 GB GDDR6X20 GB GDDR6X24 GB GDDR6X
Memory Bus128-bit192-bit?192-bit?256-bit256-bit320-bit320-bit320-bit384-bit
Memory SpeedTBATBATBA14 Gbps14 GbpsTBA19 Gbps19 Gbps19.5 Gbps
BandwidthTBATBATBA448 Gbps448 GbpsTBA760 Gbps760 Gbps936 Gbps
TGP90W?TBATBA180W?220W320W?320W320W350W
Price (MSRP / FE)$149?$199?$299?$399 US?$499 US$599 US?$699 US$899 US?$1499 US
Launch (Availability)2021?2021?2021?November 2020?29th OctoberQ4 2020?17th SeptemberJanuary 2021?24th September