There is no question that NVIDIA’s RTX 5000 GPU will be one of the biggest stories at CES 2025, and I think that Intel and AMD will come with their own new hardware. But I don’t expect each of these companies, in their own way, to put the pedal to the metal when it comes to power for their chip designs. After all, we’ve spent the last few years covering AI PC CPUs that focus on efficiency more than raw performance.

While NVIDIA RTX 5000 GPUs seem to be delivering the performance leap we’ve come to expect from its 2022-era cards, AMD is also redefining what’s possible for mobile workstations with Ryzen AI Max chipswhich combines powerful graphics with gobs of integrated memory. Intel didn’t sit still either – it finally moved Arrow Lake into the high-performance and gaming arena with its Core Ultra 200HX chipswhich can reach 24 cores and 5.5GHz speed.

I’m not just talking about power in the true sense of performance, either. NVIDIA’s $1,999 RTX 5090 requires a 1,000-watt power supply to operate and can handle up to 575 watts. Ryzen AI Max chips, on the other hand, can consume as much as 120-watts. Intel’s Core Ultra 200HX chips go up to 120-watts. Clearly, none of this hardware is for anyone worried about their energy bills or potential laptop battery life.

So what do you get for all this energy consumption? AMD says the RTX 5090 will deliver nearly twice the performance of its previous flagship, the $1,499 RTX 4090. In a 4K Cyberpunk 2077 demo with full ray tracing, the 4090 hovered around 108 fps while the 5090 reached 240 fps. That frame count is somewhat controversial, however, because the RTX 5090’s DLSS 4 AI upscaling creates three frames for every natively rendered frame. The final result may look smoother to most people, but some players may question the integrity of the so-called false frames.

It’s these same AI-generated frames that allow NVIDIA to claim that the $549 RTX 5070 can be as powerful as the 4090. That may be true when it comes to pure frames-per-second counts, but it’s certainly that it is not for rasterized performance without DLSS 4.

AMD’s Ryzen AI Max chips don’t aim for the same kind of graphical heights as NVIDIA’s new GPUs, but they still have a lot of hardware in them. The top-of-the-line Ryzen AI Max+ 395 sports 16 CPU Zen 5 cores, 50 TOPS of AI performance and 40 RDNA 3.5 GPU compute units. According to AMD, it should be part of Apple’s 14-core M4 Pro chip (and even faster in the Vray benchmark), and it is 2.6 times faster in 3D rendering than Intel’s Core Ultra 9 288V.

on an interview with AMD CVP and product CTO Joe Macrihe told Engadget that the success of Apple Silicon as a major reason why Ryzen AI Max exists. “What Apple has shown is that consumers don’t care what’s inside the box,” he said. Macri later said, “I always knew, because we built APUs, and I pushed this big APU forever, that I could build, a system smaller, faster, and I could give more high performance at the same time.

AMD too briefly previewed its RDNA 4 graphics at CES, although at this point it clearly refers to the mid-range and not to NVIDIA’s RTX 5090. In particular, AMD will debut a new AI powered upscaling technology on RDNA 4 GPUs, FidelityFX Super Resolution 4 (FSR 4). That should finally give AMD a way to compete directly against NVIDA’s DLSS, which for years has looked better than earlier versions of FSR. The first RDNA 4 cards, the Radeon RX 9070 and 9070 XT, will arrive in the first quarter.

Intel’s presence at CES 2024 was more muted than the competition, but loyalists will likely appreciate the new Core Ultra 200HX chips. While they have lowered the NPU performance from recent AI PC hardware (12 TOPS from 48 TOPS), the Core Ultra 9 285HX looks like a 24-core beast. It will be interesting to see how it competes with AMD’s Ryzen AI 300 hardware, although it doesn’t stand a chance against the Ryzen AI Max when paired with a discrete GPU.