NVIDIA, AMD, and Intel are aiming to maximize power at CES 2025

There was no doubt that NVIDIA’s RTX 5000 GPUs were going to be one of the biggest stories at CES 2025, and I think Intel and AMD will arrive with some new hardware of their own. But I didn’t expect that each of these companies, in their own way, would put the pedal to the metal when it comes to powering their chip designs. After all, we’ve spent the last few years covering AI-powered PC CPUs that were more aimed at efficiency than raw performance.

While NVIDIA RTX 5000 GPUs appear to be making the performance jump we’ve come to expect over their 2022-era cards, AMD is also redefining what’s possible for mobile workstations with Ryzen Ai Max chipswhich combines powerful graphics with amounts of built-in memory. Intel isn’t standing still either – it’s finally bringing Arrow Lake into the high-performance gaming arena with Ultra Core 200HX chipsetWhich can reach up to 24 cores and 5.5GHz speeds.

I’m not just talking about power in terms of absolute performance either. NVIDIA’s $1,999 RTX 5090 requires a 1,000-watt power supply to operate and uses up to 575 watts. Meanwhile, Ryzen AI Max chips can consume up to 120W. Intel Core Ultra 200HX chipset reaches 120W. Obviously, none of these devices are intended for anyone concerned about energy bills or the potential life of a laptop battery.

So what do you get for all this energy consumption? AMD says the RTX 5090 will deliver nearly double the performance of its previous flagship, the $1,499 RTX 4090. Cyberpunk 2077 Demo With full ray tracing, the 4090 hovered around 108fps while the 5090 hit 240fps. This frame count is a bit controversial, given that the RTX 5090’s DLSS 4 AI upgrade generates three frames for each frame rendered natively. The end result may appear smoother to most people, but some players may question the safety of so-called false framerates.

It’s the same AI-generated framerates that allow NVIDIA to declare that its $549 RTX 5070 can be as powerful as the 4090. That may be true when it comes to pure frames per second, but it certainly won’t be for rasterization. Performance without DLSS 4.

AMD’s Ryzen AI Max chips aren’t aiming for the same kind of graphical heights as NVIDIA’s new GPUs, but they’re still notable for the sheer amount of hardware they contain. The top-of-the-line Ryzen AI Max+ 395 processor has 16 Zen 5 CPUs, 50 TOPS of AI performance, and 40 RDNA 3.5 GPUs. According to AMD, it should be part of Apple’s 14-core M4 Pro chip (and even faster in Vray benchark), and it’s also 2.6 times faster in 3D rendering than the Intel Core Ultra 9 288V.

in Interview with AMD CVP and CTO Joe MacriHe told Engadget that the success of Apple Silicon is the main reason Ryzen AI Max exists. “What Apple has shown is that consumers don’t care what’s inside the box,” he said. McCrary later noted, “I always knew, because we were building APUs, and I’d been pushing for this big APU forever, that I could build a smaller, faster system, and I could deliver much higher performance at the same time. Power.”

AMD too He briefly previewed the RDNA 4 graphics At CES, though at this point it’s clearly targeting the mid-range and not NVIDIA’s RTX 5090. Notably, AMD will debut a new AI-powered upgrade technology in RDNA 4 GPUs, FidelityFX Supersolution 4 (FSR 4). This would finally give AMD a way to compete directly against NVIDA’s DLSS, which for years seemed better than previous versions of FSR. The first RDNA 4 cards, the Radeon RX 9070 and 9070 XT, will arrive sometime during the first quarter.

Intel’s presence at CES 2024 was more subdued than competitors, but loyalists will likely appreciate the new Core Ultra 200HX chipset. Even though they cut back on NPU performance compared to modern AI-enabled PCs (12pps from 48pps), the Core Ultra 9 285HX feels like a 24-core beast. It will be interesting to see how AMD’s Ryzen AI 300 hardware competes, though it likely won’t stand a chance against the Ryzen AI Max when paired with a discrete GPU.