NVIDIA GeForce RTX 4080
The Nvidia GeForce RTX 4080 is a high-end desktop graphics card based on the AD103 chip using the Ada Lovelace architecture. The 4080 offers 9,728 cores and 16 GB GDDR6X graphics memory with a 256 bit memory bus and clocked at 22.4 Gbits. The card offers a very good raytracing performance thanks to the 76 dedicated raytracing cores. For AI calculations (and DLSS 3 in games), the RTX 4080 has 304 Tensor cores.
The gaming performance is well suited for 4k60 gaming in maximum detail settings and 2k gaming with higher frame rates. Even Raytracing effects can be used with DLSS in most games. Compared to the competition, the RTX 4080 is on par with the AMD Radeon RX 7900 XT with a noticeable advantage when raytracing is used.
The AD103 chp is manufactured in the modern 4nm process at TSMC (4N with EUV) and specified with a TGP (Total Graphics Power) of 320 Watt (compared to the 450 Watt of the RTX 4090). Nvidia is recommending a 750 Watt power supply for the RTX4080.
GeForce RTX 4000 Series
|Pipelines||9728 - unified|
|Tensor / AI Cores||304|
|Core Speed||2205 - 2505 (Boost) MHz|
|Theoretical Performance||48.7 TFLOPS FP16, 48.7 TFLOPS FP32, 0.76 TFLOPS FP64|
|Cache||L2: 64 MB|
|Memory Speed||22400 effective = 1400 MHz|
|Memory Bus Width||256 Bit|
|Max. Amount of Memory||16 GB|
|Memory Bandwidth||716.8 GB/s|
|API||DirectX 12 Ultimate, Shader 12_2, OpenGL 4.6, OpenCL 3.0, Vulkan 1.3|
|Power Consumption||320 Watt|
|Transistor Count||76.3 Billion|
|Die Size||379 mm²|
|Displays||4 Displays (max.), HDMI 2.1, DisplayPort 1.4a|
|Date of Announcement||20.09.2022|
|Link to Manufacturer Page||https://www.nvidia.com/en-us/geforce/gra...|
|Predecessor||NVIDIA GeForce RTX 3080 12 GB|