NVIDIA GeForce RTX 2080 Mobile vs NVIDIA GeForce RTX 3070 Ti Laptop GPU vs NVIDIA GeForce RTX 2060 Super (Desktop)

The NVIDIA GeForce RTX 2080 for laptops is the fastest mobile graphics card for notebooks in early 2019. It is based on the desktop RTX 2080 but with reduced core speeds (-7% Boost, -9% Base). The memory appears to be similar clocked and sized. Therefore, the RTX2080 offers 2,944 shaders and 8 GB GDDR6 memory connected by a 256 bit interface (14 GHz, 448 GB/s).

A more power efficient "Max-Q" version is also planned with further reduced clock rates.

Features

NVIDIA manufacturers the TU104 chip on a 12 nm FinFET process and includes features like Deep Learning Super Sampling (DLSS) and Real-Time Ray Tracing (RTRT), which should combine to create more realistic lighting effects than older GPUs based on the company's Pascal architecture (if the games supports it). The RTX 2080 is also DisplayPort 1.4 ready, while there is also support for HDMI 2.0b, HDR, Simultaneous Multi-Projection (SMP) and H.265 video en/decoding (PlayReady 3.0).

Performance

The mobile RTX 2080 should perform a bit slower than the desktop RTX 2080 and therefore definitely faster than the old GTX 1080 for laptops. Therefore, it should be able to run all demanding games in 4k with maximum details. Raytracing features however may reduce framerates a lot.

The power consumption of the card was reduced from 215 Watt for the desktop RTX 2080 to 150 Watt. However, it is still only suited for thick and heavy gaming laptops. For thinner and lighter designs, the Max-Q variant of the RTX 2080 is intended that can be configured at 80 or 90 Watt (at much lower clock speeds).

The Nvidia GeForce RTX 3070 Ti Laptop GPU (mobile, GN20-E6, Max-P, Max-Q) is a mobile graphics card for notebooks and the refresh of the RTX 3070. It was announced early 2021 at CES and is based on the same GA104 Ampere chip as the old RTX 3070 Laptop. Compared to the old card, the newer one offers 15% more shaders but less clock speed. It will still feature the 256 Bit memory bus and 8 GB GDDR6. The RTX 3070ti is available in different power variants ranging from 80 Watt TGP with a Boost clock of 1035 MHz up to 125 Watt models with a Boost clock of 1485 MHz. However, there are even some models with a maximum TGP of 150 Watt (e.g., Acer Nitro 5).

There is no more Max-Q variant (formerly used for the low power variants) but every OEM can choose to implement Max-Q technologies (Dynamic Boost, Whispermode).

The performance depends on the TGP setting and cooling of the laptop. On average it should be somewhere between the old RTX 3070 Mobile and RTX 3080 Mobile (at similar TDP settings). Therefore, the card is best suited for QHD gaming in max details (for demanding games like Cyberpunk 2077). Less demanding games like the Farming Simulator 22 or older games should also run in 4K with max. detail settings.

The GA104 chip offers 6,144 FP32 ALUs of which half can also execute INT32 instructions (i.e. 3,072 INT32 ALUs). The RTX 3070 Ti however won't use all ALUs on the chip. With Turing all shaders could still execute FP32 or INT32 instructions. The raytracing and tensor cores on the chip were also improved according to Nvidia. The RTX 3070 Ti mobile series uses 5,888 of the 6,144 cores. The Ampere chips also include an improved 5th generation video encoder (NVENC for H.264 and H.265) and a 7th generation decoder (for various formats now including AV1).

The GA104 chip is manufactured by Samsung in 8nm (8N), which is not quite able to keep up with the 7nm node at TSMC (e.g. used by AMD and also for the professional GA100 Ampere chip).

The NVIDIA GeForce RTX 2060 for desktops (also known as RTX 2060S) is a fast mid range graphics card in the GeForce Turing line-up. Compared to the older GeForce RTX 2060 (that still remains in the line-up), the Super version adds 256 shaders and a wider memory bus with more memory (now 8 GB GDDR6). It is still based on the same TU106 chip (now fully utilized) and currently has no mobile counterpart (opposed to the mobile RTX 2060). The mobile RTX 2060 refresh only got slightly revised clock speeds but no new name.

Features

NVIDIA manufacturers the TU106 chip on a 12 nm FinFET process and includes features like Deep Learning Super Sampling (DLSS) and Real-Time Ray Tracing (RTRT), which should combine to create more realistic lighting effects than older GPUs based on the company's Pascal architecture (if the games supports it). The RTX 2060 is also DisplayPort 1.4 ready, while there is also support for HDMI 2.0b, HDR, Simultaneous Multi-Projection (SMP) and H.265 video en/decoding (PlayReady 3.0).

Performance

The average RTX 2060S performs slightly better than the old GeForce GTX 1080 and shows a clear improvement over the older RTX 2060. Therefore, the 2060 Super is positioned in the mid range and well suited for most games of 2018 in 1080p and 1440p. Compared to AMD, the RTX 2060 Super is positioned to run against the AMD RX 5700.

Power Requirements

NVIDIA specifies that the RTX 2060 Super should consume a maximum of 175 W and therefore 15 Watt more than the RTX 2060. In our tests the power consumption of the RTX 2060S was slightly lower than the old GTX 1080.