NVIDIA GeForce RTX 2070 3DMark Timespy Performance Benchmark Leaks Out – Slightly Faster Than GeForce GTX 1080

Oct 12, 2018

The first performance benchmark of NVIDIA’s upcoming GeForce RTX 2070 graphics card has been leaked. The results come from TUM APISAK and were obtained using a custom model from ZOTAC which features slightly higher clock speeds than the reference variant.

NVIDIA GeForce RTX 2070 3DMark Timespy Benchmark Leaks Out – Slightly Faster Than GTX 1080 Custom Models

The benchmark results posted by the source aren’t very clear since it only displays the overall score and not the individual graphics score. The system was configured with a Core i7-8700K and ZOTAC GeForce RTX 2070 graphics card with a reported clock speed of 1950 MHz (Boost clocks). The score was 8151 points for the entire system and as I mentioned, there are no individual scores provided since the benchmark is hidden.

Related NVIDIA GeForce GTX 1650 Ti In The Works, ASUS Custom Models Listed – Will Also Feature 4 GB Memory, Aiming The Radeon RX 580 With 75W TDP

The interesting part is that the GeForce GTX 1080 with the same CPU scores around 7500 points in 3DMark Timespy. The Core i7-8700K used here is clocked at 3.70 GHz which is the base clock of the CPU so it wasn’t overclocked and not affecting in a higher overall benchmark score. The GeForce RTX 2070 used is supposed to be a factory overclocked model so the performance can be expected to be slightly better on the new card compared to the Pascal-based GeForce GTX 1080.

NVIDIA GeForce RTX 2070 (Turing TU106 GPU) Graphics Card Specifications

The NVIDIA GeForce RTX 2070 features the TU106 GPU (TU106-400-A1) core which comprises of 2304 CUDA cores. NVIDIA’s 12nm FinFET architecture allows higher core count while retaining faster clock speeds which we have already seen on Pascal cards. The chip houses 10.6 Billion transistors which are a nice jump compared to the 7.2 Billion transistors on the Pascal GP104 GPU.

The actual clock speeds are maintained at 1410 MHz base and 1620 MHz (Up to 1710 MHz OC). The chip features 8 GB of GDDR6 (next-gen) memory featured across a 256-bit bus and clocked at 14 GB/s. This leads to a total bandwidth of 448 GB/s.

The NVIDIA GeForce RTX 2080 features just 175W TDP. Coupled with a very smooth power delivery system to avoid leakage, the chip is one of the most efficient GPU architecture ever designed for gamers. The display outputs for the card include 3 Display Port 1.4 (4K @ 120 Hz), 1 HDMI 2.0b (4K @ 60 Hz) and USB Type-C connector for the Virtual link which means that it is capable to support all next-gen displays with new standards. Power is fed through an 8 and 6 pin power connectors.

Related Be Fearful When Others Are Greedy – Are Tech Stocks Overcooked?

NVIDIA GeForce RTX/GTX "Turing" Family:

Graphics Card Name NVIDIA GeForce GTX 1660 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 (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
Die Size 284mm2 284mm2 445mm2 445mm2 545mm2 754mm2
Transistors 6.6 Billion 6.6 Billion 10.6 Billion 10.6 Billion 13.6 Billion 18.6 Billion
CUDA Cores 1408 Cores 1536 Cores 1920 Cores 2304 Cores 2944 Cores 4352 Cores
TMUs/ROPs 88/48 96/48 120/48 144/64 192/64 288/96
GigaRays 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 4 MB L2 Cache 4 MB L2 Cache 4 MB L2 Cache 6 MB L2 Cache
Base Clock 1530 MHz 1500 MHz 1365 MHz 1410 MHz 1515 MHz 1350 MHz
Boost Clock 1785 MHz 1770 MHz 1680 MHz 1620 MHz
1710 MHz OC
1710 MHz
1800 MHz OC
1545 MHz
1635 MHz OC
Compute 5.0 TFLOPs 5.5 TFLOPs 6.5 TFLOPs 7.5 TFLOPs 10.1 TFLOPs 13.4 TFLOPs
Memory Up To 6 GB GDDR5 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 12.00 Gbps 14.00 Gbps 14.00 Gbps 14.00 Gbps 14.00 Gbps
Memory Interface 192-bit 192-bit 192-bit 256-bit 256-bit 352-bit
Memory Bandwidth 192 GB/s 288 GB/s 336 GB/s 448 GB/s 448 GB/s 616 GB/s
Power Connectors 8 Pin 8 Pin 8 Pin 8 Pin 8+8 Pin 8+8 Pin
TDP 120W 120W 160W 185W (Founders)
175W (Reference)
225W (Founders)
215W (Reference)
260W (Founders)
250W (Reference)
Starting Price $219 US $279 US $349 US $499 US $699 US $999 US
Price (Founders Edition) $219 US $279 US $349 US $599 US $799 US $1,199 US
Launch March 2019 February 2019 January 2019 October 2018 September 2018 September 2018

The interesting thing to note from these specifications is that the GeForce RTX 2070 has a lower core count and slightly lower clocks than the GeForce GTX 1080. It comes with around the same TDP and power numbers but the main advantage aside from the performance advances from the Turing GPU architecture would be that the RTX 2070 would be the most affordable ray tracing graphics card, for the time being, starting at $499 US. I have heard that the RTX 2070 is going to be in good supply with several custom variants available at launch, next week. The reason is due to the Turing TU106 dies being much easier to produce compared to the flagship TU104 and TU102 GPUs.

Following are some of the custom models that will be available at launch from ASUS, MSI, and Gigabyte.