Skip to main content

Intel may already be conceding its fight against Nvidia

Two intel Arc graphics cards on a pink background.
Jacob Roach / Digital Trends

Nvidia continues to own the top-of-the-line GPU space, and the competition just hasn’t been able to, well, compete. The announcement of the impressive-sounding RTX 40 Super cards cements the lead even further.

As a result, AMD is said to be giving up on the high-end graphics card market with its next-gen GPUs. And now, a new rumor tells us that Intel might be doing the same with Arc Battlemage, its anticipated upcoming graphics cards that are supposed to launch later this year. While this is bad news, it’s not surprising at all.

Arc Battlemage leaks

First, let’s talk about what’s new. Intel kept quiet about Arc Battlemage during CES 2024, but Tom Petersen, Intel fellow, later revealed in an interview that it’s alive and well. The cards might even be coming out this year, although given Intel’s track record for not meeting GPU deadlines, 2025 seems like a safer bet. But what kind of performance can we expect out of these new graphics cards? This is where YouTuber RedGamingTech weighs in.

RedGamingTech posted a big update to Intel Arc Battlemage specs in his latest video, and it doesn’t sound particularly good for high-end gaming enthusiasts. According to the YouTuber, the specifications of the flagship chip may be significantly different compared to his previous predictions. What’s worse, it might never even be released.

Initially, RedGamingTech suggested that the top Battlemage GPU would feature 56 Xe cores and a frequency of up to 3GHz. That’s still the case, but rumor has it that there’s been a big shake-up in memory bus and cache configuration. Instead of the 256-bit bus and the 116MB of L2 cache, the YouTuber now says that we can expect a 192-bit bus, 8MB of L2 cache, and a whopping 512MB of Adamantine cache.

Adamantine cache is still pretty unknown to us at this stage, although an Intel patent that PCGamer shared details on tells us more about it. It’s essentially Level 4 cache that’s comparable to AMD’s Infinity Cache and appears to work in a similar way.

That sounds pretty good, right? With 56 Xe cores, the card would be a huge upgrade over the Arc A770 that comes with 32 cores. However, even despite this massive L4 cache, those specs already hint at a less-than-high-end flagship for Intel. With a 192-bit bus, Intel would probably stop at around 12GB of VRAM, unless it ends up feeling adventurous like AMD with the RX 7600 XT or Nvidia with the RTX 4060 Ti. (Let’s hope that it won’t.)

Regardless of whether this GPU is even real, RedGamingTech suspects that Intel may choose not to release it at all due to unsatisfactory profit margins. Instead, Intel might focus on a GPU with 40 Xe cores, a 192-bit memory bus, 18MB of L2 cache, and zero “Adamantine” cache.

Is it time for Nvidia to celebrate?

Nvidia GeForce RTX 4090 GPU.
Jacob Roach / Digital Trends

AMD is reportedly bowing out of the high-end GPU race in this next generation. Now, Intel is said to be doing the same. Where does that leave Nvidia? Right at the very top, with complete control of the enthusiast GPU market and nothing to worry about in that regard.

It’s a dream for Nvidia, but it’s not so great for us, the end users. Giving Nvidia the ability to drive up the prices as much as it wishes brought us the RTX 40-series, where the prices and the performance often just don’t add up. With zero competition at the high end, the RTX 5090 might turn out to be a terrifying monstrosity with an eye-watering price tag. After all, why wouldn’t it be? It’s not like AMD or Intel are doing anything to keep Nvidia from doing otherwise.

On the other hand, even if Intel chooses to focus on the mainstream segment, things won’t change too much. AMD is Nvidia’s main competitor, and even now, when it has a couple of horses in this race, it still can’t match Nvidia’s flagship RTX 4090, or even the surprisingly impressive new RTX 40 Super cards. Intel, now one generation behind (and soon to be two), wouldn’t have been able to beat Nvidia’s future flagship either.

For the mainstream market, meaning the vast majority of GPUs that are sold, it’s actually good if AMD and Intel will be there and give Nvidia some heat. Those prices might end up less inflated as a result. Meanwhile, high-end gaming will be pricier than ever, but unfortunately, Intel wouldn’t have been able to stop Nvidia there anyway, regardless of the card it might never release.

Editors' Recommendations

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…
Intel is cooking up an exciting DLSS 3 rival
Kena Bridge of Spirits on the Samsung Odyssey OLED G9.

Intel is working on a rival to Nvidia's DLSS 3. Intel and researchers from the University of California published a paper detailing the tech, currently dubbed ExtraSS, at Siggraph Asia 2023 (spotted by Wccftech). It accomplishes the same goal as DLSS 3 by generating new frames to improve performance. Unlike DLSS 3, however, ExtraSS uses frame extrapolation, not frame interpolation.

That latter method is how DLSS 3 (and AMD's FSR 3) works. It takes two sequential frames and compares them to generate a frame in-between. This naturally means you're playing on a slight delay, as the tech needs both the current and next frame to do its dirty work. Intel is proposing a technique that uses extrapolation, where it uses data only from previous frames to predict the next frame. That gets rid of the latency issue currently present in DLSS 3.

Read more
How I conceded to the RTX 4060 Ti
Logo on the RTX 4060 Ti graphics card.

The RTX 4060 Ti 8GB was the most disappointing GPU I reviewed this year. That was true when I reviewed it at launch, and I stand by that statement today.

But recently, I found myself recommending that same GPU to a friend of mine who was building a PC. I wasn't trying to sabotage his PC -- I promise. And so far, he's having a great time playing games with the card. So how can a GPU be both disappointing and something I'd recommend to a friend?

Read more
Intel just called out Nvidia
Intel CEO Pat Gelsinger.

There was a time when Intel and Nvidia could stay clear of each other's lanes more or less. That time is no more, especially with Intel entering the GPU race and both companies pushing forward with AI.

The new rivalry came to a head for Intel while announcing its new Core Ultra and 5th Gen Xeon chips at an event in New York City. Intel CEO Pat Gelsinger took an interesting jab at Nvidia’s CUDA technology. According to him, inference is going to surpass the importance of training for AI. He also questioned the long-term dominance of Nvidia's CUDA as an interface for training, considering it a “shallow moat that the industry is motivated to eliminate.“ Ouch. Those are fightin' words.

Read more