Ever since NVIDIA pulled the curtains back on Turing this past Monday we've been counting the days to next Monday, August 20th, when team green is set to unleash its next generation family of ray-tracing, frame crunching, GeForce 20 series gaming graphics cards.
Thankfully however, the leaks have just been pouring in over the past few days ever since the Monday reveal at Siggraph and today is no exception. This however is the absolute first leak pertaining to an actual performance score for the company's upcoming mid-range GTX 2060 5GB graphics card.
So let's get straight to it!
NVIDIA GeForce GTX 2060 5GB - GTX 1080 Performance, Now In The Mid-Range
You read that right, if these numbers are to be believed, we're looking at GTX 1080 performance in the mid-range with Turing. And not any GTX 1080 at that, but an overclocked GTX 1080. If this leaked 3DMark entry is legitimate, it indicates that what we've heard about the GTX 2060 from AdoredTV's source is actually true. Both in terms of the 5GB GDDR6 memory and the GTX prefix for the 2060.
RUMORED GeForce 20 series lineup, according to AdoredTV
NVIDIA Titan RTX – $3000 US (50% Faster Than 1080 Ti)
NVIDIA GeForce RTX 2080 8GB GDDR6 – $500-$700 US (50% Faster Than 1080)
NVIDIA GeForce RTX 2070 7GB GDDR6 – $300-$500 US (40% Faster Than 1070)
NVIDIA GeForce GTX 2060 5GB GDDR6 – $200-$300 US (27% Faster Than 1060)
NVIDIA GeForce GTX 2050 4GB GDDR5 – $100-$200 US (50% Faster Than 1050 Ti)
Although this score may contradict what we've heard about the GTX 2060 in terms of performance, which is supposed to outperform the GTX 1060 by 27% but not quite match the GTX 1080, let alone an overclocked GTX 1080.
This brings us to the caveat here. Unfortunately there's no real way of finding out if this entry is genuine and was actually created by a GTX 2060, or just a GTX 1080 that 3DMark has been tricked into thinking is a GTX 2060. Which is actually possible. We've seen manipulated entries before using some UEFI tricks. So please, remember to take this entry with a grain of salt.
Could a GTX 2060 actually match the GTX 1080 in terms of performance, perhaps a high-end factory overclocked GTX 2060 can, we simply don't know for sure right now. What we know for sure however is that with talk of NVIDIA preparing to one-up itself in the ultra high-end by launching a monstrous 4352 CUDA core RTX 2080 Ti combined with these pretty insane alleged performance figures for the GTX 2060 in the mid-range, Monday August 20th just got that much more exciting!
NVIDIA GeForce RTX 2080 & RTX 2080 Ti Confirmed & Rumored Specifications - UPDATED August 17th
| Wccftech | RTX 2080 (Confirmed) | GTX 1080 | RTX 2080 Ti (Rumored) | GTX 1080 Ti |
|---|---|---|---|---|
| Architecture | Turing | Pascal | Turing | Pascal |
| Lithography | 12nm FinFET | 16nm FinFET | 12nm FinFET | 16nm FinFET |
| GPU | TU104 (Confirmed) | GP104 | TU102 (Confirmed) | GP102 |
| CUDA Cores | 2944 (Confirmed) | 2560 | 4352 (Confirmed) | 3584 |
| TMUs | 184 (Rumored) | 160 | 272 | 224 |
| ROPs | 64 | 64 | 88 | 88 |
| Core Clock | ~1,500MHz (Rumored) ~1,700MHz (Expected) | 1607MHz | ~1,350MHz (Rumored) ~1,550MHz (Expected) | 1481 |
| Boost Clock | ~1,750MHz (Rumored) ~1,950MHz (Expected) | 1733MHz | ~1,500MHz (Rumored) ~1,750MHz (Expected) | 1582 |
| FP32 Performance (Peak) | 10.6 TFLOPS (Rumored) ~12 TFLOPS (Expected) | 8.9 TFLOPS | 13.1 TFLOPS (Rumored) ~16 TFLOPS (Expected) | ~11.3 TFLOPS |
| Memory Interface | 256-bit (Confirmed) | 256-bit | 352-bit (Confirmed) | 352-bit |
| Memory | 8GB GDDR6 (Confirmed) | 8GB GDDR5X | 11GB GDDR6 (Confirmed) | 11GB GDDR5X |
| Memory Speed | 14Gbps (Confirmed) | 10Gbps | 14Gbps (Confirmed) | 11Gbps |
| Memory Bandwidth | 448GB/s (Confirmed) | 320GB/s | 616GB/s (Confirmed) | 484.4GB/s |
| TDP | ~180W (Rumored) | 180W | ~250W | 250W |
| Launch | Q3 (August) 2018 | May 17 2016 | TBA | Mar 9 2017 |
| Launch MSRP | ~$699 (Rumored) | $599 $699 (Founder's) | TBA | $699 |
