NVIDIA, AMD and Intel look to power more at CES 2025

There was no doubt that NVIDIA’s RTX 5000 GPUs will be one of the biggest stories at CES 2025, and I thought that Intel and AMD would come with their new devices. But I don’t expect any of these companies, in their own way, to put iron on metal when it comes to their chip designs. After all, we’ve spent the last few years covering AI PC CPUs that focus more on efficiency than performance.

Although the NVIDIA RTX 5000 GPUs seem to provide the threat that we expected from its cards of the 2022 era, AMD is also explaining the possibilities for mobile applications and its own. Ryzen AI Max chipswhich combines powerful graphics with gobs of integrated memory. Intel hasn’t just been quiet – it’s finally moving Arrow Lake into the arena of high-performance gaming. Core Ultra 200HX chipswhich can reach up to 24 cores and a speed of 5.5GHz.

I’m not just talking about the power in his actions, either. NVIDIA’s $1,999 RTX 5090 requires a 1,000-watt power supply to run and consumes up to 575 watts. Ryzen AI Max chips, meanwhile, can consume up to 120-watts. Intel’s Core Ultra 200HX chips go up to 120-watts. Of course, none of these products are designed for anyone concerned about their electricity bills or laptop battery life.

So what do you get for using all this power? AMD says the RTX 5090 will offer almost twice the performance of its predecessor, the $1,499 RTX 4090. In 4K. Cyberpunk 2077 display with full tracking, the 4090 clocked 108fps while the 5090 reached 240fps. The frame count is a bit controversial, however, since the RTX 5090’s DLSS 4 AI upscaling produces three frames per frame naturally. The results may look good to most people, but some players may question the integrity of the so-called false frames.

It is the same AI-generated frames that allow NVIDIA to announce that the $549 RTX 5070 can be as powerful as the 4090. This may be true in terms of counting frames per second, but it may not be rasterized. work without DLSS 4.

AMD’s Ryzen AI Max chips don’t require the same length as NVIDIA’s new GPUs, but they’re still notable for the number of features they contain. Ryzen AI Max+ 395 16 CPU Zen 5 cores, 50 TOPS of AI performance and 40 RDNA 3.5 GPU compute units. According to AMD, it should be compatible with Apple’s 14-core M4 Pro chip (and faster in the Vray benchmark), and it is 2.6 times faster in rendering 3D than Intel’s Core Ultra 9 288V.

In interview with AMD CVP and product CTO Joe Macritold Engadget that the success of Apple Silicon as the main reason why Ryzen AI Max exists. “What Apple has shown is that consumers don’t care about what’s inside the box,” he said. Later Macri said, “I always knew, because we make APUs, and I have been pushing this big APU forever, which I can build, a small, fast system, and I can provide high performance at the same time. power.”

AMD as well briefly showed his RDNA 4 images at CES, although it’s currently targeting the mid-range and not NVIDIA’s RTX 5090. In particular, AMD will present a new AI technology leading in RDNA 4 GPUs, FidelityFX Super Resolution 4 (FSR 4). This should give AMD a way to directly compete with NVIDA’s DLSS, which for years has been superior to older FSR models. The first RDNA 4 cards, the Radeon RX 9070 and 9070 XT, will arrive sometime in the first quarter.

Intel’s presence at CES 2024 was more subdued than the competition, but loyalists will appreciate the new Core Ultra 200HX chips. While downgrading the NPU performance from its latest AI PC hardware (12 TOPS down 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 devices, although it may not stand a chance against the Ryzen AI Max when paired with a separate GPU.