Skip to main content

Nvidia may be working on a surprising new budget GPU

Nvidia GeForce RTX 3050 graphics card.
Jacob Roach / Digital Trends

This is certainly unexpected. Hints of an upcoming Nvidia graphics card showed up in the PCI-ID database, and it’s definitely not what you think. Instead of working on the RTX 50-series or refreshing a 40-series GPU, Nvidia is bringing back the slowest RTX 30-series card — the RTX 3050 — but with an Ada Lovelace chip. In theory, that could make this the first RTX 30-series GPU to have access to Deep Learning Super Sampling 3 (DLSS 3).

The GPU in question is a laptop version of the RTX 3050. It’s hard to say why Nvidia would choose to release new versions of that particular card in 2024 (or beyond), but the RTX 3050 A exists — VideoCardz found traces of it in the latest Nvidia drivers. Just the fact that there’s an RTX 3050 in the works is surprising, but that it’s based on the AD106 chip is what baffles me.

We’re most likely dealing with a cut-down version of the AD106 GPU, which has a maximum of 4,608 CUDA cores. It’s not odd for Nvidia to be using cut-down versions of this chip for another GPU, but seeing it show up in the RTX 3050 is pretty strange. The RTX 3050 appears in several versions, but the mobile card has a mere 2,048 CUDA cores. That’s quite a leap.

Get your weekly teardown of the tech behind PC gaming
Check your inbox!

The AD106M chip could have many uses within the Lovelace generation, from the RTX 4050 to the RTX 4060 Ti, so the RTX 3050 is … a choice. The most interesting implication of using Ada architecture in an Ampere card lies in DLSS 3 and Nvidia’s frame generation technology.

Nvidia's Ada Lovelace GPU.
Nvidia

DLSS 3 provides a significant improvement over DLSS 2, so it’s no wonder that Nvidia locked it to the RTX 40-series. For many, DLSS 3 provided an incentive to upgrade, and it was much-needed, as some RTX 40-series cards barely moved the needle when compared to their predecessors. It’s not just a fancy on Nvidia’s part, though. DLSS 3 needs the Ada architecture in order to run, as it uses fourth-generation Tensor cores and Nvidia’s optical flow accelerator, so everyone without an RTX 40-series card is out of luck.

This makes me wonder — could this strange, Frankensteined RTX 3050 with an Ada chip actually have access to DLSS 3? It’d be the only card outside of the RTX 40-series lineup to offer frame generation if that were the case. This would also give what would likely end up in a fairly cheap gaming laptop a lot of extra power to handle newer titles.

Technically, with an AD106 chip, it seems like it could be possible for the RTX 3050 to feature DLSS 3 — at least on the hardware side. However, I still think it’s unlikely. We don’t know when, or if, this card will appear in laptops, but chances are that it’ll be a fairly niche product, and there’s no reason for Nvidia to introduce DLSS 3 in a single older card when it has a whole lineup that features it. Although it’s impossible to say with certainty, the RTX 3050 A is most likely just Nvidia’s way to get rid of some AD106 chips before it moves on to the next generation.

Monica J. White
Monica is a UK-based freelance writer and self-proclaimed geek. A firm believer in the "PC building is just like expensive…
This toolkit just upended Nvidia’s dominance over pro GPUs
Nvidia introducing its Blackwell GPU architecture at GTC 2024.

Nvidia is the undisputed leader in professional GPU applications, and that doesn't come down solely to making the best graphics cards. A big piece of the puzzle is Nvidia's CUDA platform, which is the bedrock for everything from Blender to various AI applications. The new Scale tool, developed by Spectral Compute, aims to break down the walled garden.

Although we've seen competitors to the CUDA software stack, such as AMD ROCm, Scale is a "drop-in replacement" for CUDA. It's a compiler that allows CUDA applications to be natively compiled on AMD GPUs. Spectral Compute says Scale accepts CUDA programs as is, without the need to port to another language. In Spectral's own words, "... existing build tools and scripts just work."

Read more
Details on the upcoming AMD and Nvidia GPUs just got leaked
The RX 7900 XTX.

Seasonic, a prominent PSU manufacturer, has reportedly revealed several upcoming GPUs from AMD's Radeon RX 7000 series and Nvidia's RTX 5000 series on its website. Seasonic listed the unreleased GPUs on its Wattage Calculator webpage, mentioning at least four new AMD and five new Nvidia models, although they seem to be removed at the time of writing this article.

As per a report, Seasonic’s website referenced high-end models of AMD's forthcoming Radeon RX 7000 series, including the RX 7990 XTX, RX 7950 XTX, and RX 7950 XT. This is the first time these specific models have been spotted anywhere online, adding to the anticipation surrounding AMD's next-gen GPUs. However, it's worth noting that this isn't the first time AMD has introduced a high-end refresh. Previously, it launched the "XX50" models as part of the RDNA 2 refresh, which included the 6950 XT, 6750 XT, and 6650 XT.

Read more
AMD’s new integrated graphics just did something really impressive
A render of the new Ryzen AI 300 chip on a gradient background.

For years, any type of semi-serious gaming required having a discrete graphics card. While that's still the preferred way to do it, modern integrated GPUs can do quite a lot, as can be seen in this benchmark of the new AMD Radeon 890M. The GPU, bundled in the AMD Ryzen AI 9 HX 370 processor, may not give you Cyberpunk 2077 on ultra settings, but it can rival some of Nvidia's most popular discrete GPUs.

Of course, we're not talking about the likes of the RTX 4080 Super, but about cards from several generations ago. However, that doesn't make them any less popular in the Steam Hardware Survey. For example, Nvidia's GTX 1650 is the second-mostused GPU in the latest survey results, and it has been for some time -- and it also happens to be one of the cards that the Radeon 890M can keep up with.

Read more