The GeForce RTX 3090 Ti TUF Gaming graphics card from ASUS could be the first custom variant of the upcoming flagship to emerge. The NVIDIA GeForce RTX 3090 Ti would be the Ampere graphics lineup’s new flagship.
It will be an upgrade from the current RTX 3090, with slightly improved performance thanks to faster GDDR6X memory chips. These will also push the power envelope further than it has ever been pushed before. The ASUS GeForce RTX 3090 Ti TUF Gaming graphics card, a fully custom design for NVIDIA’s Ampere GPUs, has been spotted for the first time by its home.
The site does not provide any information on the card or a graphic representation of it. The package is the only item we can see, and it looks quite similar to the existing 3090 TUF Gaming graphics card.
Also, there is no mention of PCIe Gen 5.0 (only PCIe Gen 4.0), which was rumoured to be the highlight of the GeForce RTX 3090 Ti. However, this may still be true for Founders Edition models because only the power connector was going to be Gen 5 compliant, and most custom models use non-FE power inputs.
‘Alleged’ NVIDIA GeForce RTX 3090 Ti Specifications
Once again, the NVIDIA GeForce RTX 3090 Ti is likely to be a Titan-class GPU. The 3090 Ti is likely to have the entire GA102 GPU core with 10752 cores and 24 GB GDDR6X memory, according to the specs. Micron’s upgraded dies will allow the memory to run at higher speeds, pushing speeds over 20 Gbps.
The price may remain unchanged at $1499 US (MSRP), but we should see a slight 5% increase overall. According to a prior rumour, the GeForce RTX 3090 Ti graphics card will have a TGP of above 400W. This is 50W higher than the previous 3090, implying better GPU and VRAM rates.
There’s also talk of a brand new power connector coming in the MicroFit form factor, but it won’t look anything like the existing connector. The new 16-pin connector will be compatible with PCIe Gen 5.0 and will provide some current stability for the next-generation protocol, which is expected to debut on the flagship card.
The inclusion of 2GB GDDR6X memory modules to the NVIDIA RTX 3090 Ti is a significant development. Running at 21 Gbps will demand more power, which means higher temperatures. We’ve already seen how hot the VRAM on the GeForce RTX 3090 graphics card gets, particularly the modules on the backside.
With denser capacity modules, NVIDIA will be able to put all of the modules on the front side of the PCB (12 total), resulting in slightly lower PCB and memory temperatures. The GeForce RTX 3090 Ti won’t be the only card to get these higher density modules; according to the report, the GeForce RTX 3070 Ti will also get a 2GB module upgrade. The card’s bandwidth would be increased to 1 TB/s if it had 21 Gbps memory chips. The graphics card is expected to debut at CES 2022 and will be available on January 27th (if things go according to plan).
NVIDIA GeForce RTX 30 ‘SUPER’ Series Graphics Card Specifications (Rumored):
| Graphics Card Name | NVIDIA GeForce RTX 3090 Ti | NVIDIA GeForce RTX 3090 | NVIDIA GeForce RTX 3080 Ti | NVIDIA GeForce RTX 3080 12 GB | NVIDIA GeForce RTX 3080 | NVIDIA GeForce RTX 3070 Ti 16 GB | NVIDIA GeForce RTX 3070 Ti | NVIDIA GeForce RTX 3070 | NVIDIA GeForce RTX 3060 Ti | NVIDIA GeForce RTX 3060 | NVIDIA GeForce RTX 3050 |
| GPU Name | Ampere GA102-350? | Ampere GA102-300 | Ampere GA102-225 | Ampere GA102-220? | Ampere GA102-200 | Ampere GA104-400 | Ampere GA104-400 | Ampere GA104-300 | Ampere GA104-200 | Ampere GA106-300 | Ampere GA106-150 |
| Process Node | Samsung 8nm | Samsung 8nm | Samsung 8nm | Samsung 8nm | Samsung 8nm | Samsung 8nm | Samsung 8nm | Samsung 8nm | Samsung 8nm | Samsung 8nm | Samsung 8nm |
| Die Size | 628.4mm2 | 628.4mm2 | 628.4mm2 | 628.4mm2 | 628.4mm2 | 395.2mm2 | 395.2mm2 | 395.2mm2 | 395.2mm2 | 276mm2 | 276mm2 |
| Transistors | 28 Billion | 28 Billion | 28 Billion | 28 Billion | 28 Billion | 17.4 Billion | 17.4 Billion | 17.4 Billion | 17.4 Billion | 13.2 Billion | 13.2 Billion |
| CUDA Cores | 10752 | 10496 | 10240 | 8960 | 8704 | 6144 | 6144 | 5888 | 4864 | 3584 | 3072? |
| TMUs / ROPs | 336 / 112 | 328 / 112 | 320 / 112 | 280 / 104 | 272 / 96 | 184 / 96 | 184 / 96 | 184 / 96 | 152 / 80 | 112 / 64 | TBC |
| Tensor / RT Cores | 336 / 84 | 328 / 82 | 320 / 80 | 280 / 70 | 272 / 68 | 184 / 46 | 184 / 46 | 184 / 46 | 152 / 38 | 112 / 28 | TBC |
| Base Clock | TBA | 1400 MHz | 1365 MHz | TBA | 1440 MHz | TBA | 1575 MHz | 1500 MHz | 1410 MHz | 1320 MHz | TBC |
| Boost Clock | TBA | 1700 MHz | 1665 MHz | TBA | 1710 MHz | TBA | 1770 MHz | 1730 MHz | 1665 MHz | 1780 MHz | TBC |
| FP32 Compute | TBA | 36 TFLOPs | 34 TFLOPs | TBA | 30 TFLOPs | TBA | 22 TFLOPs | 20 TFLOPs | 16 TFLOPs | 13 TFLOPs | TBC |
| RT TFLOPs | TBA | 69 TFLOPs | 67 TFLOPs | TBA | 58 TFLOPs | TBA | 44 TFLOPs | 40 TFLOPs | 32 TFLOPs | 25 TFLOPs | TBC |
| Tensor-TOPs | TBA | 285 TOPs | 273 TOPs | TBA | 238 TOPs | TBA | 183 TOPs | 163 TOPs | 192 TOPs | 101 TOPs | TBC |
| Memory Capacity | 24 GB GDDR6X | 24 GB GDDR6X | 12 GB GDDR6X | 12 GB GDDR6X | 10 GB GDDR6X | 16 GB GDDR6X | 8 GB GDDR6X | 8 GB GDDR6 | 8 GB GDDR6 | 12 GB GDDR6 | 8 GB GDDR6 |
| Memory Bus | 384-bit | 384-bit | 384-bit | 384-bit | 320-bit | 256-bit | 256-bit | 256-bit | 256-bit | 192-bit | 128-bit |
| Memory Speed | 21 Gbps | 19.5 Gbps | 19 Gbps | 19 Gbps | 19 Gbps | 21 Gbps | 19 Gbps | 14 Gbps | 14 Gbps | 16 Gbps | TBC |
| Bandwidth | 1008 GB/s | 936 GB/s | 912 Gbps | 912 Gbps | 760 GB/s | 672 GB/s | 608 GB/s | 448 GB/s | 448 GB/s | 384 GB/s | TBC |
| TGP | 450W | 350W | 350W | 350W | 320W | ~300W | 290W | 220W | 175W | 170W | 150W? |
| Price (MSRP / FE) | $1499 US | $1499 US | $1199 | $999 US? | $699 US | $599 US? | $599 US | $499 US | $399 US | $329 US | $279 US? |
| Launch (Availability) | 27th January 2022 | 24th September 2020 | 3rd June 2021 | Q1 2022? | 17th September 2020 | Q1 2022? | 10th June 2021 | 29th October 2020 | 2nd December 2020 | 25th February 2021 | 27th January 2022 |
also read:
LG has created a spectacular soundbar that bounces sound off the ceiling for better clarity
