Skip to main content

The RTX 5070 might come with an unexpected downgrade

The Gigabyte GeForce RTX 4070 Ti Super AI Top graphics card showcased at Computex 2024.
Kunal Khullar / Digital Trends

Rumors are starting to circulate around Nvidia’s upcoming RTX 50-series GPUs, which are expected to begin rolling out later this year. Specs for the full range of desktop cards have been shared by well-known leaker kopite7kimi on X (formerly Twitter), and it looks like most of the range is set to get a downgrade in the next generation — at least in terms of core count.

The leaker shared core counts and the memory interface for the suspected range of GPUs, following up rumors for the RTX 5090 and RTX 5080 a little over a week ago. The GB205 GPU is expected to go in the RTX 5070, and the leaker claims it will come with 50 Streaming Multiprocessors (SMs). The AD104 GPU, seen in the RTX 4070, RTX 4070 Super, and RTX 4070 Ti, comes with 60 SMs.

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

Before panicking, it’s worth pointing out that these are rumored GPU specs. They aren’t specs for graphics cards. Nvidia will trim down its GPUs for different models, and we don’t have any details on how Nvidia will slice up its cards. The AD104 GPU has 60 SMs, for example, but the RTX 4070 only comes with 46. Only the RTX 4070 Ti has access to the full GPU core. We could see a similar setup in the next generation.

Things are a little more interesting lower down the stack, particularly for the GB207 GPU. This core is expected to go inside the RTX 5060, replacing the AD107 core inside the RTX 4060. It comes with 20 SMs, according to the leaker, which is a downgrade from the 24 SMs in the AD107 GPU.

Unlike higher-end GPUs, Nvidia doesn’t segment its lower-end cores as much. The RTX 4060, for instance, comes with the full AD107 core. The RTX 5060 will likely come with the full GB207 core,as well.

Kopite7kimi also claims this is the only GPU out of the range that will use GDDR6 memory, while the rest of the range will use the new GDDR7 memory standard. If these specs hold up, the RTX 5060 might struggle compared to the rest of the range given its reduced core count and older memory support.

Way too early to tell

Two RTX 4070 Ti Super graphics cards sitting next to each other.
Jacob Roach / Digital Trends

Although it’s interesting looking at rumored specs, they don’t say much about how these graphics cards will work in practice. For starters, these are just rumored specs — Nvidia hasn’t said anything about RTX 50-series GPUs outside of launching the Blackwell architecture in the data center. That’s another factor at play. RTX 50-series cards will use the new Blackwell architecture, which could bring plenty of performance improvements, even at a lower core count.

As we enter the second half of the year, it won’t be long until we know more about Nvidia’s next-gen GPUs. The rumor mill can’t quite agree on whether Nvidia will launch the cards in the back half of this year or in early 2025, but they should arrive shortly. Nvidia typically uses its fall Graphics Technology Conference (GTC) event to announce new generations of desktop graphics cards, so if we see a fall GTC event show up on Nvidia’s calendar, that’s where we’ll likely hear about RTX 50-series cards.

Jacob Roach
Lead Reporter, PC Hardware
Jacob Roach is the lead reporter for PC hardware at Digital Trends. In addition to covering the latest PC components, from…
This GPU just beat the RTX 4090 — and Nvidia didn’t make it
The board of the RTX 4090 Super graphics card.

Modders are doing what Nvidia won't. The team at Teclab put together a Frankenstein graphics card, which it calls the RTX 4090 Super, that was able to beat the RTX 4090 by 13% in benchmarks.

You can't buy this graphics card, of course, but it's an interesting look into how splicing together the best components can deliver big performance gains. The heart of the RTX 4090 Super is the RTX 4090 GPU, which is Nvidia's AD102 die. Teclab changed everything else about the graphics card, though.

Read more
This could be the reason you upgrade your GPU
The RTX 4080 in a running test bench.

Now more than ever, the best graphics cards aren't defined by their raw performance alone -- they're defined by their features. Nvidia has set the stage with DLSS, which now encompasses upscaling, frame generation, and a ray tracing denoiser, and AMD is hot on Nvidia's heels with FSR 3. But what will define the next generation of graphics cards?

It's no secret that features like DLSS 3 and FSR 3 are a key factor when buying a graphics card in 2024, and I suspect AMD and Nvidia are privy to that trend. We already have a taste of what could come in the next generation of GPUs from Nvidia, AMD, and even Intel, and it could make a big difference in PC gaming. It's called neural texture compression.
Let's start with texture compression

Read more
Why Nvidia is about to get a huge edge over AMD
The Nvidia RTX 4080 Super on a pink background.

Micron has shared some performance figures for its next-gen graphics memory, and if these numbers turn out to be true, it could mean great things for upcoming graphics cards.

The company claims that its GDDR7 VRAM will offer up to 30% performance improvement in gaming scenarios, and this reportedly applies both to games that rely heavily on ray tracing and on pure rasterization. Will Nvidia's RTX 50-series, which is said to be using GDDR7 memory, turn out to be a bigger upgrade than expected?

Read more