NVIDIA GeForce RTX 4060
The Nvidia GeForce RTX 4060 is a mid-range desktop GPU manufactured using the 5 nm process at TSMC. The AD107 chip is used here. It combines 3,072 shader units and 8 GB of GDDR6 memory. The memory interface is 128-bit, resulting in a memory bandwidth of 272 GB/s in conjunction with the VRAM clock speed.
The features that were introduced with the high-end models of the Ada Lovelace generation, such as DLSS 3.0 with frame generation, are also present in the Nvidia GeForce RTX 4060. This sets the new mid-range card apart from the Nvidia GeForce RTX 3060 and provides a significant advantage in games that offer these features.
Without DLSS, the Nvidia GeForce RTX 4060 performs slightly behind the Nvidia GeForce RTX 3060 Ti. Compared to AMD, the Nvidia GeForce RTX 4060 often competes with an AMD Radeon RX 6650 XT. The GeForce RTX 4060 caters to the 1080p gaming range in terms of performance. At times, the performance is sufficient for 1440p gaming as well, although older games are more suitable for this resolution. Additionally, some compromises in terms of graphical fidelity might be necessary for the latest games. The performance is suitable for playable frame rates at high detail settings.
The power consumption of the Nvidia GeForce RTX 4060 is specified by the manufacturer at 115 Watts (TDP). This is significantly lower than the Nvidia GeForce RTX 3060, which has a TDP of 170 watts. In comparison to the Nvidia GeForce RTX 3060 Ti (200 W TDP), the Nvidia GeForce RTX 4060 performs well and delivers similar performance with significantly lower power consumption. Power is supplied through a PCIe slot and an additional 6+2-pin connector.
GeForce RTX 4000 Series
|Pipelines||3072 - unified|
|Tensor / AI Cores||96|
|Core Speed||1830 - 2460 (Boost) MHz|
|Theoretical Performance||15.11 TFLOPS FP16, 15.11 TFLOPS FP32|
|Cache||L1: 128 KB, L2: 24 KB|
|Memory Speed||17000 effective = 2125 MHz|
|Memory Bus Width||128 Bit|
|Max. Amount of Memory||8 GB|
|Memory Bandwidth||272 GB/s|
|API||DirectX 12_2, Shader 6.7, OpenGL 4.6, OpenCL 3.0, Vulkan 1.3|
|Power Consumption||115 Watt|
|Transistor Count||18.9 Billion|
|Die Size||118.9 mm²|
|PCIe||PCIe 4.0 x8|
|Displays||4 Displays (max.), HDMI 2.1, DisplayPort 1.4a|
|Date of Announcement||18.05.2023|
|Predecessor||NVIDIA GeForce RTX 3060|