NVIDIA GeForce RTX 3050 4GB Laptop GPU vs Intel UHD Graphics Xe G4 48EUs vs Intel UHD Graphics Xe 16EUs (Tiger Lake-H)

The Nvidia GeForce RTX 3050 Laptop GPU (mobile, NVIDIA_DEV.2583, GN20-P0) is the slowest RTX 3000 mobile card and based on the GA107 Ampere chip. It offers 2048 CUDA, 16 Ray Tracing and 64 Tensor cores. The memory bus is limited to 128 Bit and supports 4 GB of GDDR6 dedicated graphics memory.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).

In early 2023 Nvidia did refresh the RTX 3050 (GN20-P0-R) with a bigger VRAM of 6GB but reduced memory bandwidth. The 3050 6GB Laptop GPU also offers 2,560 CUDA cores as the 3050 Ti mobile.

The performance should be between the old GTX 1650 Ti and the 1660 Ti Max-Q depending on the used TGP variant. Therefore, it is best suited for full HD gaming (1920 x 1080) with high detail settings in demanding games. 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 faster RTX 3050 Ti offers 25% more cores at similar clock speeds and TGP settings. 

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 Intel UHD Graphics Xe Graphics G4 (Tiger-Lake U GPU with 48 EUs) is a integrated graphics card in the low end Tiger-Lake U CPUs (15 Watt, e.g. Core i3 11th Gen). It is using the new Xe architecture (Gen12) and should be announced later in 2020.

The performance depends on the TDP settings of the laptop and the used cooling. First informations show that the chip can be configured at 15 and 28 Watt TDP default (as the Ice Lake-U chips) and the performance should be around a dedicated GeForce MX230 in 3DMark benchmarks. For gaming we are expecting a bit worse performance due to the missing dedicated graphics memory and driver support. Compared to the fastest Ice Lake iGPU (Iris Plus G7), the 48 EU version in an i3 should be slightly faster. Therefore, the iGPU is still only for lowest graphical settings and low resolutions in demanding games.

The Tiger Lake SoCs and therefore the integrated GPU are manufactured in the modern 10nm+ process (improved 10nm process) at Intel and therefore should offer a very good efficiency.

The Intel UHD Graphics Xe 750 (Rocket-Lake GPU with 16 EUs) is a integrated graphics card in the low end Tiger Lake-H CPUs. It is using the new Xe architecture (Gen12) and was announced in May 2021. This variant only uses 16 of the 32 EUs in the chip (=128 shaders) and therefore is significantly slower than the 32 EU version.

Compared to the previous generation of UHD Graphics ,the Xe architecture and the improved shader count lead to a big leap in graphics performance.