6 hidden details of the GeForce RTX 40 series that Nvidia didn’t talk about

Finally, the GeForce RTX 40 series has been unveiled, but in true Nvidia fashion, CEO Jensen Huang didn’t delve deep into raw speeds and feeds when introducing the RTX 4090 and 4080 during his GTC keynote. Heck, Huang barely talked about gaming performance. Thankfully, Nvidia’s website includes key technical details missing from the presentation – details that confirm several extremely interesting tidbits about these new “Ada Lovelace” GPU-powered graphics cards.

Here are six important details about the GeForce RTX 40 series that you should know Not heard during Jensen’s reveal. For the full look at Nvidia’s new graphics cards, check out our coverage of the GeForce RTX 4090 and 4080 announcement.

One name, two very different RTX 4080s

In a deeply anti-consumer move, Nvidia is launching two GeForce RTX 4080 offerings that rumored to differ in storage capacity. Nvidia ended up simply naming them “16GB RTX 4080” and “12GB RTX 4080”. But while Huang didn’t mention it, these two “4080s” will also offer incredibly different base performance.

As you can see in the table above, not only does the 12GB GeForce RTX 4080 have less memory, it also has a much narrower 192-bit bus and a whopping one 21 percent less CUDA cores. That means it will be significantly slower than the 16GB model in most cases. Referring to these two very different GPUs by the same name is sure to cause confusion among graphics card buyers.

The 12GB RTX 4080 may not have a Founders Edition model

NVIDIA

Speaking of which, scrolling through the spec sheet for the RTX 4080 revealed this interesting additional tidbit. While the 16GB GeForce RTX 4080 includes specific length, width, and slot measurements for Nvidia’s Founders Edition version, the 12GB GeForce RTX 4080 simply says “varies by manufacturer.” It doesn’t sound like the 12GB model will get Nvidia’s own Founders Edition treatment. (The sound you hear is the ghost of EVGA screaming).

The GeForce RTX 40 series supports AV1 encoding

NVIDIA

AV1 encoding is the holy grail for media creators, offering much better graphics at a much lower bandwidth footprint. Intel has beaten AMD and Nvidia by adding killer AV1 encoding to its Arc graphics cards, but footnotes to Nvidia’s RTX 4090 and 4080 datasheets indicate that Team Green will support this generation with AV1 encoding as well (AV1 decoding was already supported).

“GeForce RTX 4090 and GeForce RTX 4080 graphics cards feature two of our new 8th generation NVIDIA encoders (NVENC), now with support for AV1 encoding, opening up a range of new possibilities for live streamers, video editors and video callers” , so the RTX 40 series announcement mail crowded.

You read that right – not one, but two NVENC encoder with AV1 encoder support in RTX 40 series graphics cards. Attention streamers.

DLSS 3 is not coming for older GPUs

It is obvious that last generation GPUs do not contain new generation hardware encoders. But Nvidia’s much-touted DLSS 3 software feature isn’t coming to the RTX 20 and 30 series cards either, although DLSS 2.0 and 2.1 have been backported to both. Nvidia’s GPU generation comparison page only lists DLSS 3 on the RTX 40 series, while older-gen RTX offerings remain listed with DLSS 2.0.

NVIDIA

Nvidia confirmed in a statement to The Verge that DLSS 3 will not be backward compatible. “DLSS 3 is powered by the new fourth-gen Tensor Cores and Optical Flow Accelerator on GeForce RTX 40-series GPUs,” and therefore won’t come for older RTX generations, Nvidia spokesman Benjamin Berraondo told the website.

You will need a bigger boat

The GeForce RTX 4090 doesn’t draw more than 600 watts, as some early rumors suggested – at least not in Nvidia’s Founders Edition iteration – but it does does are rated at 450W, with a minimum 850W power supply recommended. That matches the last-gen flagship RTX 3090 Ti. Like we said back then, you’re going to need a bigger boat. And by boot we mean the power supply. It’s not all expensive news, however. While the RTX 40 Series supports the 12VHPWR pin connectors found in new ATX 3.0 power supplies, you can also use three or four standard 8-pin power connectors if you already have a beefy power supply.

NVLink is dead for GeForce

Nvidia’s SLI technology for multi-GPU setups has been dead for a while, but the “NVLink” technology that replaced it stayed in last-gen RTX 3090 GPUs. No longer. The spec pages for the GeForce RTX 4090 and 4080s specifically say NVLink is Not support this generation. Pour one out.

That’s it for these buried treasures. We’ll certainly be hearing more about the GeForce RTX 40 series in the coming days and weeks, but again, for the full rundown of Nvidia’s new graphics cards, check out our coverage of the GeForce RTX 4090 and 4080 announcements on.