December 7, 2022


Inspire the Next

Nvidia ‘Unlaunches’ the RTX 4080 12GB GPU

This web site might gain affiliate commissions from the inbound links on this page. Terms of use.

With the start of Nvidia’s RTX 4080 GPUs, plural, on the horizon, the company has taken an unprecedented step: It is “unlaunching” the RTX 4080 12GB. As you may remember, this GPU was widely mocked for getting a RTX 4080 when giving specs comparable to former x70 GPUs. That consists of making use of a smaller Ad104 die, a great deal fewer CUDA cores, and a slim 192-bit memory bus. No person was content with this scenario, as Nvidia has hardly ever provided two GPUs with the similar title and diverse specs right before. Why it chose to do so this time will be a mystery for the ages. Regardless, it has now responded by removing the GPU from its steady. It is unclear if it will be rebadged as an RTX 4070, or just disappear completely. As of press time, the GPU has been deleted from Nvidia’s internet site.

Nvidia announced the abrupt u-transform in a blog write-up. We double-checked to make absolutely sure it wasn’t a parody web page, as it is astonishing Nvidia listened to its buyers. The firm holds the lion’s share of the discrete GPU industry, so it can pretty a lot do whichever it wishes. This time, however, it appears to be to have long gone as well far.

In its post, the business states the apparent: “The RTX 4080 12GB is a great graphics card, but it is not named ideal. Acquiring two GPUs with the 4080 designation is confusing.” Um, you are just now figuring this out, Nvidia? We understood it was bewildering on start day and stated as a lot. The rest of the web site just reiterates the 16GB variation is nonetheless coming. Nvidia has also supplied it a start day: Nov. 16. The business states that if the extended traces at Microcenters for the 4090 start are any indicator, the 16GB edition will definitely offer out, much too. It is almost certainly correct about that. RTX 4090s are previously littering eBay with $1,000 additional to the price tag. It would seem that even even though mining is lifeless, scalping is even now alive and very well.

RTX 40-sequence spec comparison.

As you can see earlier mentioned, the two GPUs are radically various. In all preceding generations, the 12GB card would be labeled as an RTX 4070. Nvidia hasn’t begun speaking about that distinct GPU nevertheless, so it’s nevertheless possible it could flip into a single. Nonetheless, it’s also likely it will be scuttled totally. We dislike to beat a dead horse, but it is stuff like this that most likely served EVGA make your mind up it was time to stop producing Nvidia GPUs. It appears to be like partners will have to have already made some of these GPUs, as the start was just weeks away. Also, the 12GB edition was a companion-only card, with Nvidia abstaining from building FE versions. This most likely designed the decision much easier as it had no skin in the match.

The timing of the announcement can make us think Nvidia is reading through to the 4080 benchmarks it posted on its website. Just about every web site that handles this things qualified prospects with a headline about how substantially slower the 12GB model is than the 16GB model. This just bolstered the plan in everyone’s minds that the 12GB design was a dollars seize. Would any gamer really pay $899 for a GPU with a 192-little bit memory bus? You could possibly assume which is spec minutia that no one pays awareness to, but a person paying that considerably dollars on a GPU would know that. Nvidia’s announcement arrives on the heels of an online uproar more than these benchmarks, making us consider the two gatherings are connected.

F1 22 DLSS 3 benchmarks, simply click to broaden. (Image: Nvidia)

There is also yet another reason for Nvidia to backpedal. Instead of just executing the ideal thing to cut down consumer confusion, the company is probably just hoping to stay away from launching a dud. AMD is about to unveil its RDNA3 GPUs on Nov. 3. According to Igor’s Lab, the firm will not be equipped to touch the RTX 4090. Nevertheless, its flagship GPU may well stop up proper in the center of both Nvidia RTX 4080s. Remember the 16GB model is $1,199 and the 12GB product was $899. Now visualize AMD placing a card in between these two that performs nearer to the superior-close, at a rate of $700 or so. That would make the 12GB card DOA right away.

Regardless of its motivations, Nvidia has accomplished the ideal point right here. Launching a $900 card with x70 specs experienced led to accusations of Nvidia being greedy. That was an accusation hurled at the enterprise during the pandemic way too, as it did things like relaunching the RTX 3080 with a $500 price quality, alongside with all the numerous Ti card launches. We know that firms have to have to make a revenue, but presenting “new” GPUs with a five to 10 per cent general performance improve above an current card seems pointless. Nvidia even bragged to buyers in that interval about how its clients were being spending $300 far more than standard to upgrade. Back again then, it bought each individual GPU it made, so it attempted to make as many playing cards as it could. This aided guide to the present oversupply of GPUs.

For now, we will have to hold out and see what happens with the RTX 4070. Nvidia will probably just sit back again and see what AMD announces on Nov. 3 and then change appropriately. It’s by now still left huge gaps concerning its 40-series GPUs. There is a large delta among the RTX 4090 and 4080, so a 4080 Ti is possibly in the playing cards. We presently know a 4090 Ti will appear at some place, also. Wherever AMD’s chiplet-based GPUs will fit into this matrix stays to be observed.

Now Go through: