chrome 66FqDePbGB

Any links to online stores should be assumed to be affiliates. The company or PR agency provides all or most review samples. They have no control over my content, and I provide my honest opinion.

Nvidia is determined to cover every option possible in the GPU market in an attempt to keep AMD at bay.   There are currently five RTX models available and three GTX models for this Turing generation.

Nvidia is now expanding that choice to include an additional three options with a new Super moniker, and I wouldn’t be surprised if they add a few new Ti models before the next generation.

The new Super models come in the form of the RTX 2060 SUPER, RTX 2070 SUPER, and RTX 2080 SUPER and sit above the standard model but below a Ti model.

The 2070 and 2060 models will launch on the 2nd of July with the no current launch data for the RTX 2080 SUPER.

The GeForce RTX 2070 SUPER is using TU104 GPU with 2560 CUDA cores. This model comes with the same memory configuration as RTX 2070 Non-Super: 8GB GDDR6 256-bit with 14 Gbps bandwidth. This SKU will require 30W more than its predecessor (215W)

The RTX 2060 SUPER is now featuring TU106 GPU with 2176 CUDA cores. The Wattage has increased by 15W to 175W. The biggest change came to memory configuration. Unlike RTX 2060 Non-Super the new card has 8GB GDDR6 memory across a 256-bit interface.

In regards to the RTX 2080 SUPER it has only been mentioned and there has been a claim of 15 Gbps which is higher than any other RTX card.

Both SKUs (2070S and 2060S) will be available on July 9th. On the same day, the embargo on AIC cards will lift. Only Founders Edition models reviews will be posted on July 2nd. Pricing information is not available yet.

It is however believed the new cards will lead to a drop in price with the older cards, which is claimed to increased competition with the up and coming AMD cards. The timing of the launch is also suspiciously close to the AMD RX 5700 launch, and Nvidia clearly wants to steal some of the hype.

The new Super cards are claimed to be around 15% faster than the standard models sitting below them.

RTX line-up

GPUCUDAMemoryMemory Speed
TITAN RTXTU102-400 4608 24GB G6 384b 14 Gbps
RTX 2080 TiTU102-300 4352 11GB G6 352b 14 Gbps
RTX 2080 SUPER (TBC)TU104-450 3072 8GB G6 256b 15 Gbps
RTX 2080TU104-400 2944 8GB G6 256b 14 Gbps
RTX 2070 SUPERTU104-410 2560 8GB G6 256b 14 Gbps
RTX 2070TU106-400 2304 8GB G6 256b 14 Gbps
RTX 2060 SUPERTU106-410 2176 8GB G6 256b 14 Gbps
RTX 2060TU106-300 1920 6GB G6 192b 14 Gbps

Full specification

Graphics Processing Clusters5 or 63
Texture Processing Clusters2017
Streaming Multiprocessors4034
CUDA Cores (single precision)25602176
Tensor Cores320272
RT Cores4032
Texture Units184136
ROP Units6464
Rays Cast7 Giga Rays/second6 Giga Rays/second
Base Clock1605 MHz1470 MHz
Boost Clock1770 MHz1650 MHz
Memory Clock7000 MHz7000 MHz
Memory Data Rate14 Gbps14 Gbps
L2 Cache Size4096 K4096 K
Total Video Memory8192 MB GDDR68192 MB GDDR6
Memory Interface256-bit256-bit
Total Memory Bandwidth448 Gb/s448 Gb/s
Texture Rate (Bilinear)326 GigaTexels/s246 GigaTexels/s
Fabriaction Process12nm FFN12 nm FFN
Transistor Count13.6 Billion10.8 Billion
Connectors3x DisplayPort
1x USB Type-C
2x DisplayPort
1x Dual-Link DVI
1x USB Type-C
Form FactorDual SlotDual Slot
Power ConnectorsOne 6-pin, One 8-pinOne 8-pin
Recommended Power Supply650 Watts550 Watts
Total Graphics Power (TGP)215 Watts175 Watts

Similar Posts