New leaks about the rumored RTX 4060 Ti have left many PC gamers scratching their heads. Not only does the GPU not sound very impressive so far, it also demonstrates Nvidia’s commitment to an odd option: the 12-pin power connector. Yep, it’s the exact same thing that’s been getting a lot of media coverage lately.
Seeing this bizarre decision makes me wonder – is Nvidia’s commitment to the high-end segment really the right way?
a warm answer
The news about the upcoming RTX 4060 Ti is out thanks to a reliable leaker, kopite7kimi on Twitter. Even so, it’s important to remember that nothing has been confirmed until Nvidia talks itself, and even then, it’s still not exactly final until it hits the shelves, as the “unlaunched” RTX 4080 12GB has taught us.
With that disclaimer out of the way, let’s take a look at what the Twitter whistleblower shared. According to the tweet, the RTX 4060 Ti will have AD106-350-A1 GPU and will come with 4,352 CUDA cores as well as only 8GB of GDDR6 memory at 18Gbps. Kopite7who didn’t mention it, but previous leaks predicted a 128-bit memory bus – that’s a bandwidth of 288GB/s. The card has a much increased cache compared to the previous iteration and is now 32MB instead of 4MB.
Needless to say, the overall response of the internet has been lukewarm so far. A quick look at the RTX 3060 Ti tells us why. The previous generation card also comes with 8GB of GDDR6 memory, has more cores (4,864) and can have more bandwidth (448GB/s to 288GB/s) due to the 256-bit bus. Note that the 4060 Ti’s bandwidth is even more unconfirmed than the rest of the leak, so proceed with caution.
In any case, these specs aren’t very impressive, but the increase in cache will definitely be an improvement. But there is more.
Doubling down on a controversial decision?
The leaker noted that the board has a “very short reference board” and still uses the CEM5 connector. That’s what made me stop.
This means that Nvidia may still be using the new 12VHPWR connector we know from the RTX 4090 and RTX 4080, and this is despite the fact that the 4060 Ti is said to come with a total card power (TBP) of 220 watts.
For reference, there have been cases where the connectors melted on the RTX 4090 and the problem is thought to be the 12VHPWR connector. Nvidia hasn’t made any official statements about it, other than that it’s investigating the issue and the issue hasn’t spread widely, but I can’t help wondering why Nvidia uses this connector.
Assuming that the RTX 4060 Ti does indeed come with a 220 watt TBP, there is no need for Nvidia to use this connector in the first place. In fact, Nvidia also used a 12-pin connector (though different, without the four extra “sense pins”) on the RTX 3060 Ti – but Nvidia’s board partners didn’t follow their lead and the majority went for an 8-pin design instead.
Sticking with an 8-pin connector would certainly be enough for a fairly middle-of-the-pack card. In fact, I wouldn’t be surprised if Nvidia’s partners once again go with an 8-pin design for the RTX 4060 Ti and only use Founders Edition cards, Nvidia’s 12-pin solution.
High-end cards for a mid-range market
In this generation, the prices of Nvidia’s cards leave a lot to be desired. We have the RTX 4090 starting at $1,600 and the RTX 4080 starting at $1,200. Somehow, the pricing of these cards It makes the RTX 4090 look like a good deal, but it’s not – both GPUs are way too expensive.
Nvidia’s approach so far could not be more different from Intel’s. Intel is a new player in the GPU market and Arc Alchemist GPUs are far from a widespread success, but a recent interview with Raja Koduri from Intel is somewhat thought provoking. Coderi made Intel’s stance clear – it’s not the way to go super high to target most PC manufacturers.
“High tech has no limits right now. What is the definition of high-end? 600 watts? Frankly, our partners and customers want some halo SKUs for bragging rights, and we always like to find ways to enable it,” Koduri told Gadgets360. “But my priority at this point is to get to the core audience with a single power connector. That can get you 200 to 225W.”
The Intel executive isn’t wrong—the “core audience” isn’t made up of people who will buy $1,600 cards like the RTX 4090. The RTX 4060, RTX 4060 Ti, and RTX 4070 are the cards you’ve been waiting for. To get the most out of this generation, this should be the market Nvidia is trying to meet with good pricing and adequate specs.
So far, in terms of specs, the RTX 4060 Ti is shaping up to be pretty average, and we also have an odd choice of power connectors. However, if Nvidia can keep this card affordable, it will likely already be successful.
Unfortunately, the price of the first two cards in the Ada series doesn’t give me much hope for the rest of the series. Let’s hope the new AMD RX 7900 XTX will piss Nvidia off a bit and motivate it to keep prices reasonable.