In a new rumor by Videocardz, it is stated that NVIDIA’s GeForce RTX 3090 SUPER will be launching as the GeForce RTX 3090 Ti. The card is going to be the new flagship aimed at enthusiasts.
NVIDIA GeForce RTX 3090 Ti To Feature An Entirely New Board Design With Single-Sided Memory, New Power Connectors & PCIe 5.0 Interface, Alleges Rumor
It looks like NVIDIA isn’t going to give its flagship GeForce RTX 3090 graphics card the SUPER series branding but rather, release a new variant with the ‘Ti’ series branding. Most of the specs that have leaked out in rumors remain the same except the board design which is likely getting some major upgrades.
NVIDIA GeForce RTX 3090 Ti ‘Alleged’ Specifications
First up, we have the NVIDIA GeForce RTX 3090 Ti and this is expected to be a Titan-class card once again. Kopite7kimi had previously stated that NVIDIA is unlikely to use use the 3090 SUPER naming convention & go with something else considering that this is one of their top-tier product so the ‘Ti’ branding makes sense.
As for the specs, 3090 SUPER is expected to rock the full GA102 GPU core with 10752 cores and 24 GB GDDR6X memory. The memory will be faster-clocked thanks to improved dies from Micron, pushing speeds past 20 Gbps. The pricing may be kept the same at $1499 US (MSRP) but overall, we are looking at a minor 5% improvement. A previous rumor also stated that the GeForce RTX 3090 SUPER graphics card will feature a TGP of over 400W. That’s 50W more than the existing 3090 which means that we could be looking at faster clocks on GPU and VRAM.
Now, this is all that we have known for a while now so what’s changed you ask? Well first up, we got a rumor of a brand new power connector that will come in the MicroFit form factor but it isn’t going to look anything like the existing connector. The new 16-pin connector will be PCIe Gen 5.0 ready & will offer some current stability for the next-gen protocol which is expected to be introduced on the flagship card.
A major change for the NVIDIA GeForce RTX 3090 Ti would be the addition of 2GB GDDR6X memory modules. Running at 21 Gbps will require more power and more power translates to higher temps. We have already seen how the VRAM temperatures on GeForce RTX 3090 graphics card gets and especially the modules featured on the back-side. Having denser capacities modules will mean that NVIDIA could feature all the modules on the front side of the PCB (12 modules in total) which will yield slightly lower PCB and memory temperatures. The GeForce RTX 3090 Ti won’t be the only card getting these higher density modules as the rumor also mentions the GeForce RTX 3070 Ti to get a similar 2GB module treatment.
As for the launch, the NVIDIA GeForce RTX 3090 Ti is expected to launch in January along with the RTX 3070 Ti 16 GB and RTX 2060 12 GB.
NVIDIA GeForce RTX 30 ‘SUPER’ Series Graphics Card Specifications (Rumored):
Graphics Card Name | NVIDIA GeForce RTX 3060 | NVIDIA GeForce RTX 3060 Ti | NVIDIA GeForce RTX 3070 | NVIDIA GeForce RTX 3070 Ti | NVIDIA GeForce RTX 3070 Ti 16 GB | NVIDIA GeForce RTX 3080 | NVIDIA GeForce RTX 3090 | NVIDIA GeForce RTX 3090 Ti/SUPER? |
---|---|---|---|---|---|---|---|---|
GPU Name | Ampere GA106-300 | Ampere GA104-200 | Ampere GA104-300 | Ampere GA104-400 | Ampere GA104-400 | Ampere GA102-200 | Ampere GA102-300 | Ampere GA102-350? |
Process Node | Samsung 8nm | Samsung 8nm | Samsung 8nm | Samsung 8nm | Samsung 8nm | Samsung 8nm | Samsung 8nm | Samsung 8nm |
Die Size | TBC | 395.2mm2 | 395.2mm2 | 395.2mm2 | 395.2mm2 | 628.4mm2 | 628.4mm2 | 628.4mm2 |
Transistors | TBC | 17.4 Billion | 17.4 Billion | 17.4 Billion | 17.4 Billion | 28 Billion | 28 Billion | 28 Billion |
CUDA Cores | 3584 | 4864 | 5888 | 6144 | 6144 | 8704 | 10496 | 10752 |
TMUs / ROPs | 112 / 64 | 152 / 80 | 184 / 96 | 184 / 96 | 184 / 96 | 272 / 96 | 328 / 112 | 336 / 112 |
Tensor / RT Cores | 112 / 28 | 152 / 38 | 184 / 46 | 184 / 46 | 184 / 46 | 272 / 68 | 328 / 82 | 336 / 84 |
Base Clock | 1320 MHz | 1410 MHz | 1500 MHz | 1575 MHz | TBA | 1440 MHz | 1400 MHz | TBA |
Boost Clock | 1780 MHz | 1665 MHz | 1730 MHz | 1770 MHz | TBA | 1710 MHz | 1700 MHz | TBA |
FP32 Compute | 13 TFLOPs | 16 TFLOPs | 20 TFLOPs | 22 TFLOPs | TBA | 30 TFLOPs | 36 TFLOPs | TBA |
RT TFLOPs | 25 TFLOPs | 32 TFLOPs | 40 TFLOPs | 44 TFLOPs | TBA | 58 TFLOPs | 69 TFLOPs | TBA |
Tensor-TOPs | 101 TOPs | 192 TOPs | 163 TOPs | 183 TOPs | TBA | 238 TOPs | 285 TOPs | TBA |
Memory Capacity | 12 GB GDDR6 | 8 GB GDDR6 | 8 GB GDDR6 | 8 GB GDDR6X | 16 GB GDDR6X | 10 GB GDDR6X | 24 GB GDDR6X | 24 GB GDDR6X |
Memory Bus | 192-bit | 256-bit | 256-bit | 256-bit | 256-bit | 320-bit | 384-bit | 384-bit |
Memory Speed | 16 Gbps | 14 Gbps | 14 Gbps | 19 Gbps | 21 Gbps | 19 Gbps | 19.5 Gbps | 21 Gbps |
Bandwidth | 384 GB/s | 448 GB/s | 448 GB/s | 608 GB/s | 672 GB/s | 760 GB/s | 936 GB/s | 1008 GB/s |
TGP | 170W | 175W | 220W | 290W | ~300W | 320W | 350W | 450W |
Price (MSRP / FE) | $329 US | $399 US | $499 US | $599 US | $599 US? | $699 US | $1499 US | $1499 US |
Launch (Availability) | 25th February 2021 | 2nd December 2020 | 29th October 2020 | 10th June, 2021 | Q1 2022? | 17th September 2020 | 24th September 2020 | Q1 2022? |
[ad_2]