NVIDIA Unleashes GeForce RTX 4060 Ti In 8 GB & 16 GB Flavors, $399 & $499 US Pricing, 70% Faster Than 3060 Ti

NVIDIA has officially announced its GeForce RTX 4060 Ti series graphics cards which come in 8 GB & 16 GB flavors, starting at just $399 US.

The NVIDIA GeForce RTX 4060 Ti replaces the GeForce RTX 3060 Ti as the new mainstream offering which is targeted at gamers who want to enjoy the fastest 1080p gaming performance & also enter 1440p gaming with the power of DLSS 3. With prices starting at $399 US, the GeForce RTX 4060 Ti is a great option for users who are running older GPUs such as GTX 1060, RTX 2060, and even the RTX 3060 as you get more performance, better features, and mind-blowing efficiency.

The NVIDIA GeForce RTX 4060 Ti is also the first graphics card within the RTX 40 series which will be getting two memory variants. While the RTX 4080 was technically the first, the 12 GB variant got un-launched and was rebranded as the RTX 4070 Ti. The RTX 4060 Ti on the other hand will come in 16 GB and 8 GB flavors.

NVIDIA GeForce RTX 4060 Ti Graphics Card Specifications

So starting with the specifications, NVIDIA's GeForce RTX 4060 Ti graphics card is the first to feature the AD106 GPU (350-A1 variant). This GPU is also based on the TSMC 4N process node, measures 190mm2, and features 22.9 Billion transistors which are more transistors than the GA103 GPU that measured 496mm2.

This particular chip features 34 SMs with a total of 4,352 cores. It's not the full chip which houses 36 SMs with a total of 4,608 cores but that could be used for a future SKU. The chip features 136 TMUs, 48 ROPs, 136 Tensor Cores, and clocks in at a 2310 MHz base & 2535 MHz boost. This AD106 GPU can hit a peak compute performance of 22 TFLOPs (FP32), 51 RT TFLOPs & a peak Tensor performance of 353 TOPs.

As for the memory, the graphics card will come in the aforementioned 16 GB and 8 GB variants. It is configured across a 128-bit wide bus interface. The memory modules run at 18 Gbps, delivering total memory bandwidth of 288 GB/s. As for the TDP, the card is rated at 160W and the 16 GB GPU features a 5W higher TDP at 165W. Both cards make use of a PCIe Gen 4 x8 connection and power is provided through a single PCIe Gen5 cable.

NVIDIA GeForce RTX 4060 Ti Founders Edition Design

Looking at the design of the new Founders Edition cooler, I would say it's pretty much what you'd expect by now. This is a slightly refined cooling solution in a chassis that looks beautiful. With dual slots to accommodate and two axial-tech fans, this cooler should be enough for the GPU and even take it for a spin with manual overclocking. You still get a single HDMI port, three DP ports and the power connector is the standard Gen5 plug which is slightly different than the 12VHPWR connector but it does give you the peace of mind of not having to deal with the newer connector and all the latching troubles that come with it.

The 8 GB variant of the RTX 4060 Ti will be the only one to get the Founders Edition variant and the 16 GB model will only be available in custom AIB flavors.

Massive L2 Cache Resolves Memory Bandwidth Bottlenecks

Coming back to the memory, the 128-bit bus interface might seem like a downgrade over the 256-bit bus on the previous-gen 60 Ti cards but NVIDIA states that the effective bandwidth of the RTX 4060 Ti is increased to 554 GB/s, an increase of 23.5% over the 3060 Ti. This is made possible by upgrading the L2 cache from 4 MB to 32 MB, an 8x increase.

Increasing the L2 cache allows NVIDIA to overcome some of the bandwidth limitations & memory bottlenecks associated with using a narrower bus interface. You see, when the cores work, they're required to have a fast and effective channel to transfer data through and L1 is the closest and low latency lane that sits right next to them. But sitting close to the cores means you can't increase their size by a lot and if the cores can't find the data that they want on the L1 cache, they move over to the L2 cache which is right next to the L1 cache, and has a larger capacity. The memory resides on the same GPU die and is connected via a high-speed interconnect across all GPCs to send data through and forth.

NVIDIA GeForce RTX 4060 Ti Prototype With 2 MB L2 Cache (128-bit bus):

NVIDIA GeForce RTX 4060 Ti Reference With 32 MB L2 Cache (128-bit bus):

If the data is found on the L2 cache, then that's considered a cache hit but if the cores still can't find the data on the L2 cache, that's considered a cache miss and the cores need to go out of the GPU & access the main memory pool (VRAM) to find the data. This taxes the memory subsystem leading to bandwidth bottleneck. NVIDIA's solution to address this bottleneck is to increase the L2 cache. This allows the GPU cores to have more room to travel before burdening the VRAM with a limited 128-bit bus interface.

NVIDIA showcases how the increased L2 cache helps the GeForce RTX 4060 Ti by demonstrating the memory subsystem load on a reference 32 MB L2 variant against a prototype 2 MB L2 variant against each other. Both cards have the same 128-bit bus interface with 512 KB of L2 cache tied to each 32-bit memory controller.

The 32 MB L2 variant was able to reduce traffic by 40% to 60% over the performance of the 2 MB variant. The 2 MB variant was able to fill up its entire pool of L2 cache quickly and that meant that more data was going to the VRAM, causing additional traffic burden compared to the 32 MB cache variant which not only had fewer cache misses but also led to fewer traffic going to the VRAM. So even with a 128-bit bus interface, you are getting far higher bandwidth resulting in far better GPU performance than a traditional 128-bit card.

NVIDIA GeForce RTX 4060 Ti Gaming Performance, Only 140W Average Power!

Moving over to gaming performance, NVIDIA wants you to make good use of those DLSS 3, RT & Tensor cores to really feel the power of Ada. With all the RTX goodness, you can achieve up to a 70% performance increase over the RTX 3060 TI at the same price and a 2.6x increase over the older RTX 2060 SUPER. If you want to play without DLSS 3, then you are still getting a 15% perf boost which should put you around the same performance levels as an RTX 3070 but with much lower power draw.

How low you might ask? The NVIDIA GeForce RTX 3060 Ti averaged around 205W power while the RTX 3070 averaged around 250W power while gaming. The RTX 4060 Ti in comparison is said to consume just 140W on average. That's a -32% decrease in power which means you can enjoy all your favorite games while saving power and running cool and efficiently.

NVIDIA GeForce RTX 4060 Ti 8 GB Graphics Card Performance (Official):

NVIDIA GeForce RTX 4060 Ti 16 GB Graphics Card Performance (Official):

Now the NVIDIA GeForce RTX 4060 Ti is ultimately a 1080p gaming graphics card but the 16 GB variant does warrant a higher resolution or the use of better image quality in titles. NVIDIA states that the 16 GB variant can allow for higher presets in more demanding games such as A Plague Tale Requiem and Resident Evil IV Remake.

A Great 1080p Package With All The RTX Features You'd Ever Want

So summing up today's announcement, I think the NVIDIA GeForce RTX 4060 Ti graphics cards are really for users who are looking to upgrade their older GTX 1060 or RTX 2060 series cards. They do offer some amazing features with over 400 RTX titles and 300+ DLSS titles including 50 DLSS 3 titles and more that are on the way.

You get NVIDIA Studio support for content creation readiness, AV1 hardware & great AI generative performance thanks to those powerful tensor cores. NVIDIA will be leveraging its AI hardware for more advanced features such as Neural Rendering in future DLSS 3 updates, Neural Textures, and much more to come. The NVIDIA GeForce ecosystem & Game Ready driver updates are a major plus to recommending an RTX card to gamers too.

NVIDIA's GeForce RTX 4060 Ti 8 GB graphics card will be hitting retail shelves in several on the 24th of May for a price of $399 US. The 16 GB variant will be available in July for $499 US and is aimed at users who think they could use the additional memory either for gaming or for content creation purposes.