NVIDIA GeForce RTX 2070 Mobile vs NVIDIA GeForce GTX 1650 Mobile vs NVIDIA GeForce GTX 1650 Ti Max-Q

The NVIDIA GeForce RTX 2070 for laptops is the second fastest mobile graphics card for notebooks in early 2019. It is based on the desktop RTX 2070 but with reduced core speeds (-11% Boost, -14% Base). The memory appears to be similar clocked and sized. Therefore, the RTX2070 offers 2,304 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 available with further reduced clock rates.

In April 2020 Nvidia refreshed the RTX 2070 with new "Super" cards. In addition to the RTX 2070 Super Mobile with 2560 shaders, Nvidia also introduced a slightly higher clocked RTX 2070 for laptops (N18E-G1R-A1, TU106-735-A1 chip) with a 1,305 base and 1,485 MHz boost clock.

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 2070 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 2070 should perform a bit slower than the desktop RTX 2070 and therefore on par the old GTX 1080 for laptops. Therefore, it should be able to run all demanding games in 4k with high details. Raytracing features however may reduce framerates a lot.

The Nvidia GeForce GTX 1650 for laptops is a mobile graphics card that is based on the Turing architecture (TU117 chip). Compared to the faster RTX 2000 GPUs (e.g. RTX 2060), the 1650 integrates no Raytracing or Tensor cores. The performance should be slightly faster than the old GeForce GTX 1050 Ti. Compared to the desktop version, the mobile GTX1650 can use all 1024 shaders of the TU117 chip, but there are also versions with 896 shaders.

Starting March 2020, the GTX 1650 Mobile is also available with fast 12 Gbits GDDR6 graphics memory (N18P-G61, 896 shaders) as a refresh.

The Turing generation did not only introduce raytracing for the RTX cards, but also optimized the architecture of the cores and caches. According to Nvidia the CUDA cores offer now a concurrent execution of floating point and integer operations for increased performance in compute-heavy workloads of modern games. Furthermore, the caches were reworked (new unified memory architecture with twice the cache compared to Pascal). This leads to 50% more instructions per clock and a 40% more power efficient usage compared to Pascal.

Compared to the bigger Turing chips (like the TU116 of the GTX 1660 Ti and the RTX lineup), the TU117 does not include the new NVENC encoder but an older one similar to the one used in Pascal and Volta.

The power consumption of the 1650 for laptops is specified at 50 Watt TGP (Total Graphics Power) by Nvidia and therefore 15 Watt higher than the efficient (and slower) Max-Q variant of the 1650. The TU117 chip is manufactured in 12nm FFN at TSMC.

The Nvidia GeForce GTX 1650 Ti Max-Q (N18P-G62) is a dedicated mid range graphics card for laptops based on the Turing architecture. The Max-Q variant is the power saving version of the mobile GTX 1650Ti with reduced clock speeds, performance and of course power consumption. It is using the same TU117 chip with 1,024 shaders. Therefore, it is intended for thin and light gaming laptops. Compared to the faster RTX 2000 GPUs (e.g. RTX 2060), the 1650 Ti integrates no Raytracing or Tensor cores.

There are two variants of the 1650Ti Max-Q, one with 35 Watt and 1035 - 1200 MHz and a faster 40 Watt version with a clock speed of 1200 - 1365 MHz. Both however are significantly lower clocked than the normal Max-P version with 50 / 55 Watt and 1350-1385 MHz. The memory is most likely clocked at 1250 MHz = 10,000 MHz effective (Gbps) in most laptops, although there might be versions with 1500 MHz = 12,000 Gbps.

The Turing generation did not only introduce raytracing for the RTX cards, but also optimized the architecture of the cores and caches. According to Nvidia the CUDA cores offer now a concurrent execution of floating point and integer operations for increased performance in compute-heavy workloads of modern games. Furthermore, the caches were reworked (new unified memory architecture with twice the cache compared to Pascal). This leads to 50% more instructions per clock and a 40% more power efficient usage compared to Pascal.

Compared to the bigger Turing chips (like the TU116 of the GTX 1660 Ti and the RTX lineup), the TU117 does not include the new NVENC encoder but an older one similar to the one used in Pascal and Volta.

The power consumption of the 1650 Ti Max-Q laptops is specified at 35 Watt TGP (Total Graphics Power) by Nvidia and therefore 25 Watt lower than the mobile GTX 1650 Ti in the same package (other variants can reach up to 80 Watt).