NVIDIA GeForce RTX 4060 series is based on AD106-350 or AD107-400 GPUs. The latter contains 3072 CUDA cores which will be used in the RTX 4060. The Ti variant will get up to 4352 cores according to sources.
NVIDIA GeForce RTX 4060 Ti and RTX 4060 GPUs, based on Ada architecture, will have a full retail launch in May. However, NVIDIA has not announced any exact dates yet.
The RTX 4060 Ti will use the AD106-350-A1 GPU, which is a modified, cut-down version of the AD106 graphics card. It will include 34 SMs or 4352 CUDA cores, and a memory capacity of 8GB of GDDR6 memory at 18 Gbps on a 128-bit bus interface.
So, the card has a bandwidth of 288 GB/s. It also features 32MB of L2 cache, which is 8 times more than the last-gen GeForce RTX 3060 Ti.
According to some rumors, the graphics card will utilize the PG190 SKU 361 PCB. A leaked image revealed that the reference Founders Edition will use the standard 16-pin 12VHPWR connector. On the other hand, the custom models can opt for the standard 8-pin connectors or the newer 16-pin plugs.
8-pin connectors are considerably cheaper, so it makes sense to go for those since AIBs want to maximize production value of their designs. The RTX 4060 Ti will have a TDP ranging from 150-160W, which is a 25% decrease from the RTX 3060 Ti.
The RTX 4060 will use the AD107-400-A1 GPU, which is the fully enabled AD107 Ada die. The card will feature 3072 CUDA cores and 8GB of GDDR6 memory running at 18 Gbps across a 128-bit interface.
So, the card will have 288 GB/s bandwidth and feature 24 MB of L2 cache. The RTX 4060 will have a lower TDP of 110-115W. It should have a 35% lower TGP as compared to its predecessor, RTX 3060 12GB.
In terms of its PCB design, some sources said it would use the PG173 SKU 371 PCB. Like the Ti model, even the non-Ti variant would use the standard 8-pin connectors. The Mini-ITX variants of the card would make up for an efficient gaming PC.
A couple of images featuring the RTX 4060 Founder’s Edition were leaked. However, NVIDIA has not revealed any plans to launch its RTX 4070 models.
About Nvidia
NVIDIA Corporation is an American multinational technology company incorporated in Delaware, based in Santa Clara, California. They design graphics processing units (GPUs) for the gaming and professional markets, as well as system on chip units (SoCs) for the mobile computing and automotive market.
Best known for the “GeForce” lines of GPUs, they are a direct competitor to AMD’s “Radeon” series. NVIDIA has also expanded its offerings with its handheld game consoles Shield Portable, Shield Tablet, and Shield Android TV and its cloud gaming service GeForce Now.
No Comments on NVIDIA GeForce RTX 4060 Ti ‘AD106-350’ GPU will have 160W TDP