NVIDIA GeForce RTX 2080 Ti 11 GB and RTX 2080 8 GB Graphics Cards Core Specifications Confirmed – 2080 Ti With TU102 GPU Rocks 4352 CUDA Cores, 2080 With TU104 Rocks 2944 CUDA Cores
The specifications of NVIDIA's upcoming GeForce RTX 2080 Ti and RTX 2080 graphics cards are now confirmed by Videocardz. The graphics cards which are expected to be announced on 20th August will be the first major leap in GPU design by NVIDIA, featuring their latest Turing GPU architecture.
NVIDIA Turing GPU Based GeForce RTX 2080 Ti Comes With 11 GB GDDR6 Memory and 4352 Cores, GeForce RTX 2080 Comes With 8 GB GDDR6 Memory and 2944 Cores
Starting off with the details, we know that there will be at least two high-performance graphics cards from NVIDIA announced on Monday during their GeForce Celebration event. These cards were confirmed to be the GeForce RTX 2080 Ti and GeForce RTX 2080.
Both graphics cards are based on the 12nm Turing GPU architecture and will be a major leap from previous GeForce GPUs in terms of design and technologies they have to offer. We will learn more about these features during the event so let's take a look at the core specifications of these cards.
NVIDIA GeForce RTX/GTX "Turing" Family:
Graphics Card Name | NVIDIA GeForce GTX 1650 | NVIDIA GeForce GTX 1660 | NVIDIA GeForce GTX 1660 SUPER | NVIDIA GeForce GTX 1660 Ti | NVIDIA GeForce RTX 2060 | NVIDIA GeForce RTX 2070 | NVIDIA GeForce RTX 2080 | NVIDIA GeForce RTX 2080 Ti |
---|---|---|---|---|---|---|---|---|
GPU Architecture | Turing GPU (TU117) | Turing GPU (TU116) | Turing GPU (TU116) | Turing GPU (TU116) | Turing GPU (TU106) | Turing GPU (TU106) | Turing GPU (TU104) | Turing GPU (TU102) |
Process | 12nm FNN | 12nm FNN | 12nm FNN | 12nm FNN | 12nm FNN | 12nm FNN | 12nm FNN | 12nm FNN |
Die Size | 200mm2 | 284mm2 | 284mm2 | 284mm2 | 445mm2 | 445mm2 | 545mm2 | 754mm2 |
Transistors | 4.7 Billion | 6.6 Billion | 6.6 Billion | 6.6 Billion | 10.6 Billion | 10.6 Billion | 13.6 Billion | 18.6 Billion |
CUDA Cores | 896 Cores | 1408 Cores | 1408 Cores | 1536 Cores | 1920 Cores | 2304 Cores | 2944 Cores | 4352 Cores |
TMUs/ROPs | 56/32 | 88/48 | 88/48 | 96/48 | 120/48 | 144/64 | 192/64 | 288/96 |
GigaRays | N/A | N/A | N/A | N/A | 5 Giga Rays/s | 6 Giga Rays/s | 8 Giga Rays/s | 10 Giga Rays/s |
Cache | 1.5 MB L2 Cache | 1.5 MB L2 Cache | 1.5 MB L2 Cache | 1.5 MB L2 Cache | 4 MB L2 Cache | 4 MB L2 Cache | 4 MB L2 Cache | 6 MB L2 Cache |
Base Clock | 1485 MHz | 1530 MHz | 1530 MHz | 1500 MHz | 1365 MHz | 1410 MHz | 1515 MHz | 1350 MHz |
Boost Clock | 1665 MHz | 1785 MHz | 1785 MHz | 1770 MHz | 1680 MHz | 1620 MHz 1710 MHz OC | 1710 MHz 1800 MHz OC | 1545 MHz 1635 MHz OC |
Compute | 3.0 TFLOPs | 5.0 TFLOPs | 5.0 TFLOPs | 5.5 TFLOPs | 6.5 TFLOPs | 7.5 TFLOPs | 10.1 TFLOPs | 13.4 TFLOPs |
Memory | Up To 4 GB GDDR5 | Up To 6 GB GDDR5 | Up To 6 GB GDDR6 | Up To 6 GB GDDR6 | Up To 6 GB GDDR6 | Up To 8 GB GDDR6 | Up To 8 GB GDDR6 | Up To 11 GB GDDR6 |
Memory Speed | 8.00 Gbps | 8.00 Gbps | 14.00 Gbps | 12.00 Gbps | 14.00 Gbps | 14.00 Gbps | 14.00 Gbps | 14.00 Gbps |
Memory Interface | 128-bit | 192-bit | 192-bit | 192-bit | 192-bit | 256-bit | 256-bit | 352-bit |
Memory Bandwidth | 128 GB/s | 192 GB/s | 336 GB/s | 288 GB/s | 336 GB/s | 448 GB/s | 448 GB/s | 616 GB/s |
Power Connectors | N/A | 8 Pin | 8 Pin | 8 Pin | 8 Pin | 8 Pin | 8+8 Pin | 8+8 Pin |
TDP | 75W | 120W | 125W | 120W | 160W | 185W (Founders) 175W (Reference) | 225W (Founders) 215W (Reference) | 260W (Founders) 250W (Reference) |
Starting Price | $149 US | $219 US | $229 US | $279 US | $349 US | $499 US | $699 US | $999 US |
Price (Founders Edition) | $149 US | $219 US | $229 US | $279 US | $349 US | $599 US | $799 US | $1,199 US |
Launch | April 2019 | March 2019 | October 2019 | February 2019 | January 2019 | October 2018 | September 2018 | September 2018 |
NVIDIA GeForce RTX 2080 Ti 11 GB Graphics Card - The Flagship 2018 Turing Based Gaming Graphics Card
The NVIDIA GeForce RTX 2080 Ti aims to be the flagship gaming graphics card based on the Turing GPU architecture for 2018. I say gaming because there might be a Titan that comes out with better specifications and the Quadro RTX 6000 and RTX 8000 cards are already configured with better specifications but for gaming solely, this would be the card to get if you're looking to get the best bang for the buck.
The card will feature the TU102 GPU core, same as the ones on the higher-end Quadro parts. The chip will be configured with 4352 CUDA cores so that's slightly less than the full-on configuration of 4608 CUDA cores we saw on the Quadro variants. This means the ROP/TMU count would be lower too. In terms of memory, the card will feature 11 GB of GDDR6 memory which is the same VRAM size as the GeForce GTX 1080 Ti but the faster 14 Gbps DRAM dies would enable for a higher band-width of 616 GB/s compared to 484 GB/s. This will be running across a 352-bit memory bus which is a cut-down version compared to the 384-bit bus on the Quadro cards.
Based on leaks, we can expect the TDP of this card to be around 225-250W and would require dual 8-pin power connectors to boot. We have already seen several custom variants that feature a dual 8 pin configuration so that is expected.
NVIDIA GeForce RTX 2080 8 GB Graphics Card - Hitting The Sweet Spot of High-End Gaming Performance
The GeForce RTX 2080 is based on the Turing TU104 GPU and it can now be confirmed that the TU104-400-A1 isn't the full chip but a slightly cut down variant of the Quadro RTX 5000 graphics card. The card will feature 2944 CUDA cores, an 8 GB GDDR6 memory clocked at 14 Gbps and a 256-bit bus interface. This would allow for 448 GB/s of bandwidth.
This card is said to be using an 8+6 pin power connector configuration which was suggested once again by the leaked PCB. We can extrapolate that the TDP would be somewhere in between 180-210W which is reasonable for a **-104 GPU. We do not know what the final clocks would be like but guesses are somewhere in the range of 1.8-1.9 GHz for boost and further that can be achieved through overclocking. We know that GDDR6 has the potential to reach speeds north of 20 Gbps so that will be an interesting tech worth checking out by overclockers.
Overall, the specifications look like we are looking at a big boost in core count and most probably, the architecture itself is going to further increase the per SM and per core performance, delivering us increased performance across all gaming segments which include HDR, VR, 4K/5K, Ray Tracing and much more. You can check out tons of custom cards that were unveiled by our friends at the Videocardz here!