NVIDIA GeForce RTX 3050 6GB Laptop GPU vs NVIDIA GeForce RTX 2070 Super (Desktop) vs NVIDIA GeForce RTX 3080 Ti Laptop GPU

The Nvidia GeForce RTX 3050 6GB Laptop GPU (mobile, GN20-P0-R, 2023 Refresh) is the refresh of the RTX 3050 4GB Laptop GPU (slowest RTX 3000 mobile card) and also based on the GA107 Ampere chip. The 6GB variant offers more CUDA cores (2,560, +25%) but a cut down memory bus to 96 Bit. The clock speed depends on the TGP variant and can range from 713 - 1530 (base) and 1058 - 1740 (boost) for the TGP variants of 35 to 80 Watt (see table below).

The performance is between the old 4GB RTX 3050 and the RTX 3050 Ti and therefore best suited for full HD gaming (1920 x 1080) in medium to high graphic settings. The performance is not sufficient to enable Raytracing in most games, but the Tensor cores can be used for DLSS in some games (and get performance boost with slight quality reduction). Beware, that the low TGP variants will offer a significantly lower performance.

The GA107 chip offers 3,072 FP32 ALUs of which half can also execute INT32 instructions (i.e. 1,536 INT32 ALUs). The RTX 3050 however maybe 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 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 GA107 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 2070 Super (RTX 2070S) is a high-end desktop graphics card and refresh of the 2018 RTX 2070. The card is now behind the RTX 2080 Ti and RTX 2080 Super (upcoming) as the third-fastest graphics card in the Nvidia lineup of consumer cards. It uses the big TU104 chip instead of the TU106 of the RTX 2070 and offers more cores (2,560 versus 2,304).

Features

NVIDIA manufactures 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 can (if the games supports it). The RTX 2070S is 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 performance of the RTX 2070S is slightly better than the old GeForce GTX 1080 Ti. With the new ray-tracing and tensor cores, the RTX 2070S is clearly the better choice. The RTX 2070 Super is positioned in the high-end segment and therefore most current games should run fluently in 4k and high detail settings (but without ray tracing). Compared to AMD offerings, the RTX 2070 Super is aimed against the AMD Radeon RX 5700 XT (Navi).

Power Requirements

NVIDIA estimates that the RTX 2070S should consume a maximum of 215 W (RTX 2070 - 175 Watt). In our gaming tests, the RTX 2070 Super was more power-efficient than the old GeForce GTX 1080 Ti (339 versus 296 Watt for the test system running The Witcher 3).

The Nvidia GeForce RTX 3080 Ti Laptop GPU or 3080 Ti Mobile (for laptops, GN20-E8) is the fastest graphics card for notebooks in early 2022. It is based on the GA103S Ampere chip and offers 7,424 shaders and 16 GB GDDR6 graphics memory with a 256 Bit memory bus. It supports PCIe 4.0 and will be available in different variants (80 - 175 Watt TGP currently known). The maximum Boost clock can vary from 1125 (80 W) to 1590 MHz (150W and up).

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. Thanks to the higher core count, the RTX 3080 Ti should be clearly faster than the old RTX 3080 Mobile and therefore well suited for 4K gaming.

The GA103S chip offers 7,424 FP32 ALUs of which half can also execute INT32 instructions (i.e. 3,712 INT32 ALUs). With Turing all shaders could still execute FP32 or INT32 instructions. The GA103S integrates 58 Raytracing cores and 232 Tensor cores (e.g., for DLSS). The L2 cache is 4 MB. 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). Compared to the GA103, the GA103S integrates only a 256 Bit memory bus.

The GA103S 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).