The AMD Radeon RX 6800 XT is a high-desktop GPU based on the RDNA2 architecture and uses the Navi 21 chip which is manufactured in 7nm at TSMC. The GPU has 4,608 shader units, as well as 16 GB of GDDR6 VRAM with a 256-bit interface (16 Gbps, 512 GB/s).
Features. RDNA2 serves as the basis for the Navi 21 graphics chip, which is the successor to the Navi 10 graphics chip from the previous RX 5700 series. A number of new features like SAM (Smart Access Memory) and the Infinity Cache make the RX 6800 series very interesting. PCI Express 4.0 and RIS (Radeon Image Sharpening) are still available. The new Media Engine lets you decode video at up to 8K resolution, and the new Display Engine supports screens up to 8K at 60Hz including HDR or 4K HDR at 144Hz.
Performance. The performance of the AMD Radeon RX 6800 XT is comparable to a Nvidia GeForce RTX 3080. In the internal duel, the RX 6800 XT clearly surpasses the performance of a Radeon RX 5700 XT. This makes the RX 6800 XT suitable for 4K gaming.
Power consumption
The power consumption of the AMD Radeon RX 6800 XT is quantified by the manufacturer at 300 watts (TGP) and is thus somewhat more economical than the GeForce RTX 3080 (320 watts).
The NVIDIA GeForce RTX 4050 Laptop GPU (codename GN21-X2) is a mid-range laptop GPU. It is based on the AD107 chip and uses the Ada Lovelace architecture. The RTX 4050 Laptop offers 2560 shaders and uses 6 GB GDDR6 dedicated graphics memory with a clock speed of 16 Gbps (effective) and a 96 Bit memory bus. The TGP (Total Graphics Power) can be configured between 35 and 115 Watt (+ 10-25 Watt Dynamic Boost from the CPU) leading to different performance levels. The boost clock depends on the TGP settings and ranges from 1605 MHz (35 Watt) to 2370 MHz (115 Watt). The performance therefore is also highly depending on the laptop and TDP settings.
In our benchmarks, the RTX 4050 stays slightly behind the older mobile RTX 3060 but is clearly faster than the mobile RTX 3050 Ti. Therefore, it is best suited for 1920x1080 gaming at high to ultra settings depending on the game (see benchmarks below).
The RTX 4050 offers 80 tensor cores and therefore supports DLSS 3 including frame generation that can have a big impact in supported games. The raytracing cores however will see less usage, as the RTX 4050 does not offer enough performance for high detail settings and raytracing in demanding games.
The AD107 chip is manufactured in 5nm at TSMC (4N process).
The NVIDIA GeForce RTX 4090 Laptop GPU (Codename GN21-X11) is a high-end laptop GPU. It is based on the AD103 chip as the desktop RTX 4080 and use the Ada Lovelace architecture. The AD103 chip offers a maximum of 10.752 shaders from which inly 9728 are used (e.g., the RTX 4080 Desktop uses 9.728) and a 256 Bit memory bus. The RTX 4090 mobile uses 16 GB GDDR6 dedicated graphics memory with a clock speed of 20 Gbps (effective). The TGP (Total Graphics Power) can be configured between 80 and 150 Watt (+ 15 Watt Dynamic Boost from the CPU) leading to different performance levels (the desktop RTX 4080 uses 320 Watt for comparisons).
The performance depenends on the TGP settings which defines the maximum boost clock (1455 MHz for 80W and up to 2040 MHz for 150W). With 150W the performance should be in the region of the desktop RTX 4080 and therefore best suited for 4k60 or 2k with 120 fps for demanding games. For raytracing, lower resolutions or DLSS is needed.
In our reviews, an average RTX 4090 is clearly the fastest mobile GPU and bests the RTX 4080 Laptop GPU and mobile RTX 3080 Ti easily. 4090M GPUs with lower power limit can however loose up to 20% performance.
In games, fast RTX 4090 models allow gaming in 4k with maximum details. Adding Raytracing may lead to frame rates below 60 fps (e.g. F1 23) and therefore the use of DLSS or reduced settings are advised.
The AD103 chip of the RTX 4090 mobile is manufactured in an improved 5 nm process at TSMC (4N).