NVIDIA is prepping to expand its GeForce RTX 30 lineup with three new graphics cards, the RTX 3090, RTX 3070 Ti 16 GB & RTX 3050, in January.
NVIDIA GeForce RTX 3090, RTX 3070 Ti 16 GB & RTX 3050 Launching In January, Leaked Documents Confirm
The leaked information comes from Videocardz who has managed to obtain the embargo documents for NVIDIA's upcoming graphics cards based on the Ampere graphics architecture. These three new cards include the hotly anticipated and the new flagship, the RTX 3090 Ti along with RTX 3070 Ti 16 GB and RTX 3050.
Each graphics card is aimed at its own set of users with the NVIDIA GeForce RTX 3090 Ti aimed at the ultra-enthusiast GPU segment, the RTX 3070 Ti 16 GB aiming at the high-end segment while the RTX 3050 will be aimed at the mainstream segment. The launch / unveil dates of these graphics cards are mentioned below:
- NVIDIA GeForce RTX 3090 Ti: 27th January 2022 (On Shelve Date)
- NVIDIA GeForce RTX 3070 Ti 16 GB: 17th December (Unveil) / 11th January (Launch)
- NVIDIA GeForce RTX 3050: 4th January (Unveil) / 27th January (Launch)
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. As for the specs, 3090 Ti 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 Ti 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.
There's also been 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. Having 21 Gbps memory chips would essentially give the card up to 1 TB/s of bandwidth.
NVIDIA GeForce RTX 3070 Ti 16 GB Graphics Card Specifications
The NVIDIA GeForce RTX 3070 Ti 16 GB on the other hand is going to feature the GA104-401-A1 GPU. The NVIDIA GeForce RTX 3070 Ti will utilize the PG141-SKU10 board. The Ampere GPU will feature 6144 CUDA cores or 48 SMs. These are 4% more CUDA cores than the GeForce RTX 3070 & around 30% lower cores than the GeForce RTX 3080. The card features clock speeds of 1580 MHz base & 1770 MHz boost.
The NVIDIA GeForce RTX 3070 Ti will also feature 16 GB GDDR6X memory and what's important here is the fact that NVIDIA is utilizing the higher-grade GDDR6X chips rather than the standard GDDR6 modules featured on the existing GeForce RTX 3070 graphics card. The NVIDIA GeForce RTX 3070 Ti will end up close to the RTX 3080 with a TGP of 300W considering the increased cores & the newer memory modules. The card will retain a 256-bit bus interface and pin speeds will be rated at 19 Gbps like the GeForce RTX 3080 and the RTX 3080 Ti.
The standard RTX 3070 comes with a single 8-pin connector while the RTX 3070 Ti rocks a 12-pin micro-fit power interface and also a brand new PCB design which is similar to the irregular PCB designs featured on the RTX 3080, RTX 3080 Ti, and RTX 3090.
NVIDIA GeForce RTX 3050 8 GB Graphics Card Specifications
Coming to the specifications of the GeForce RTX 3050, there are reports of an NVIDIA GA106-150 GPU for the 'PG190 SKU 70' board being cooked up. The GA106-150 GPU allegedly features 3072 CUDA cores in 24 SM units.
It is also reported that the card might end up with 8 GB GDDR6 memory which gives it a big memory advantage over AMD and Intel entry-level parts. The card is expected to offer performance faster than the GeForce GTX 1660 SUPER but will be slower than the RTX 2060 12 GB variant which also launched yesterday.
Based on these specifications, the NVIDIA GeForce RTX 3050 is going to be competitive against AMD's Navi 24 (Radeon RX 6500 / Radeon RX 6400) and Intel's Alchemist DG2-128 (ARC A380) graphics cards which launch next year too. What will be interesting is to see whether prices can be maintained for these budget tier cards though we shouldn't keep our hopes high as supply issues aren't expected to be resolved till 2023.
NVIDIA GeForce RTX 30 Series Graphics Card Specifications
| 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 | NVIDIA GeForce RTX 3070 | NVIDIA GeForce RTX 3060 Ti | NVIDIA GeForce RTX 3060 Ti | NVIDIA GeForce RTX 3060 | NVIDIA GeForce RTX 3060 | NVIDIA GeForce RTX 3050 | NVIDIA GeForce RTX 3050 6 GB |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| GPU Name | Ampere GA102-350? | Ampere GA102-300 | Ampere GA102-225 | Ampere GA102-220 | Ampere GA102-200 | Ampere GA104-400 | Ampere GA104-300 | Ampere GA104 | Ampere GA104-200 Ampere GA103-200 | Ampere GA106-300 | Ampere GA106 | Ampere GA106-150 | Ampere GA107-325 |
| Process Node | Samsung 8nm | Samsung 8nm | 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 (GA104) | 276mm2 | 276mm2 | 276mm2 (GA106) | 200mm2 (GA107) |
| Transistors | 28 Billion | 28 Billion | 28 Billion | 28 Billion | 28 Billion | 17.4 Billion | 17.4 Billion | 17.4 Billion | 17.4 Billion (GA104) | 13.2 Billion | 13.2 Billion | 13.2 Billion (GA106) | 8.7 Billion (GA107) |
| CUDA Cores | 10752 | 10496 | 10240 | 8960 | 8704 | 6144 | 5888 | 4864 | 4864 | 3584 | 3584 | 2560 | 2048 |
| TMUs / ROPs | 336 / 112 | 328 / 112 | 320 / 112 | 280 / 104 | 272 / 96 | 184 / 96 | 184 / 96 | 152 / 80 | 152 / 80 | 112 / 64 | 112 / 64 | 80 / 32 | TBD |
| Tensor / RT Cores | 336 / 84 | 328 / 82 | 320 / 80 | 280 / 70 | 272 / 68 | 184 / 46 | 184 / 46 | 152 / 38 | 152 / 38 | 112 / 28 | 112 / 28 | 80 / 20 | TBD |
| Base Clock | 1560 MHz | 1400 MHz | 1365 MHz | TBA | 1440 MHz | 1575 MHz | 1500 MHz | 1410 MHz | 1410 MHz | 1320 MHz | 1320 MHz | 1552 MHz | TBD |
| Boost Clock | 1860 MHz | 1700 MHz | 1665 MHz | TBA | 1710 MHz | 1770 MHz | 1730 MHz | 1665 MHz | 1665 MHz | 1780 MHz | 1780 MHz | 1777 MHz | 1470 MHz |
| FP32 Compute | 40 TFLOPs | 36 TFLOPs | 34 TFLOPs | TBA | 30 TFLOPs | 22 TFLOPs | 20 TFLOPs | 16 TFLOPs | 16 TFLOPs | 13 TFLOPs | 13 TFLOPs | 9.1 TFLOPs | TBD |
| RT TFLOPs | 74 RFLOPs | 69 TFLOPs | 67 TFLOPs | TBA | 58 TFLOPs | 44 TFLOPs | 40 TFLOPs | 32 TFLOPs | 32 TFLOPs | 25 TFLOPs | 25 TFLOPs | 18.2 TFLOPs | TBD |
| Tensor-TOPs | TBA | 285 TOPs | 273 TOPs | TBA | 238 TOPs | 183 TOPs | 163 TOPs | 192 TOPs | 192 TOPs | 101 TOPs | 101 TOPs | 72.8 TOPs | TBD |
| Memory Capacity | 24 GB GDDR6X | 24 GB GDDR6X | 12 GB GDDR6X | 12 GB GDDR6X | 10 GB GDDR6X | 8 GB GDDR6X | 8 GB GDDR6 | 8 GB GDDR6X | 8 GB GDDR6 | 12 GB GDDR6 | 8 GB GDDR6 | 8 GB GDDR6 | 6 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 | 128-bit | 96-bit |
| Memory Speed | 21 Gbps | 19.5 Gbps | 19 Gbps | 19 Gbps | 19 Gbps | 19 Gbps | 14 Gbps | 19 Gbps | 14 Gbps | 16 Gbps | 15 Gbps | 14 Gbps | 14 Gbps |
| Bandwidth | 1008 GB/s | 936 GB/s | 912 Gbps | 912 Gbps | 760 GB/s | 608 GB/s | 448 GB/s | 608 GB/s | 448 GB/s | 384 GB/s | 240 GB/s | 224 GB/s | 168 GB/s |
| TGP | 450W | 350W | 350W | 350W | 320W | 290W | 220W | 175W | 175W | 170W | 150W | 130W (GA106) 115W (GA107) | 70W |
| Price (MSRP / FE) | TBD | $1499 US | $1199 | $999 US? | $699 US | $599 US | $499 US | $399 US | $399 US | $329 US | TBD | $249 US | TBD |
| Launch (Availability) | 29th March 2022? | 24th September 2020 | 3rd June 2021 | 11th January 2022 | 17th September 2020 | 10th June, 2021 | 29th October 2020 | October 2022 | 2nd December 2020 | 25th February 2021 | October 2022 | 27th January 2022 | 2024 |
News Source: Videocardz
