With him Blackwell An architecture well-established in AI data centers, cloud services, workstations and desktop/laptops, Nvidia's CES 2026 press event will likely be less focused on new launches. Rather, the company is expected to delve into improvements, roadmap signals, and how it plans to advance its hardware and software stack in the coming year.
Nvidia has confirmed that founder and CEO Jensen Huang will deliver the CES opening keynote on January 5, the day before the main CES show floor opens. CES has become one of the most important stages of the year for Nvidia, even if the company is not launching a new generation of GPUs.
As in previous years, this is where Nvidia is expected to lay out its priorities in gaming, artificial intelligence, data centers and new platforms. In addition to the keynote, Nvidia will also maintain a strong presence at CES with potential demos and presentations.
Here's a quick look at what Nvidia might have in store for us next month.
RTX 50 Super
If Nvidia has any news about consumer GPUs at CES 2026, it will most likely focus on RTX 50 Super. According to leaks and reports, the Super Update was originally scheduled for launch at the end of 2025 to suit the holiday season.
However, given rising memory prices and Nvidia's own history of distributing updates, a delay to early to mid-2026 now looks more likely, with CES serving as a showcase rather than a launch event.
The RTX 50 Super is not expected to bring any major changes. Instead, it looks like a minor update to Blackwell's existing GPUs, with tweaked specs aimed at making the line more balanced. The RTX 40 Super update followed a similar pattern, and current leaks suggest Nvidia is taking the same approach again.
Based on what's been revealed so far, Nvidia is expected to focus on individual SKUs rather than a full refresh. Rumored models include the RTX 5070 Super, RTX 5070 Ti Super, and RTX 5080 Super. The RTX 5070 Super is expected to move to a higher VRAM configuration, potentially 18GB, which will solve one of the biggest problems with the standard model.
The RTX 5080 Super is rumored to retain a similar core design, but could come with 8GB of additional memory for a total of 24GB, as well as higher bandwidth, possibly bringing it closer to the RTX 5090 in real-world workloads rather than pure computing.
| Video card | RTX 5080 Super | RTX 5070 Ti Super | RTX 5070 Super |
| Architecture | Blackwell GB203 | Blackwell GB203 | Blackwell GB205 |
| video memory | 24 GB GDDR7 | 24 GB GDDR7 | 18 GB GDDR7 memory |
| VRAM bus width | 256-bit | 256-bit | 192-bit |
| CUDA colors | 10,752 | 8960 | 6400 |
| TGP | 415 W | 350 W | 275 W |
Any performance gains are expected to be modest. Small clock speed jumps and minor core changes are more likely than significant increases in CUDA. The goal appears to be to smooth out compositional gaps rather than to provide a clear generational leap.
Memory configuration is one of the main reasons why the update exists at all. As games and software continue to use more memory, some RTX 50 models are already under pressure. The super update will give Nvidia the ability to adjust these configurations without changing the underlying architecture.
However, the timing remains uncertain. Higher memory costs make it difficult to change configurations without raising prices, giving Nvidia a clear incentive to wait. As a result, CES 2026 is more likely to bring confirmation rather than availability.
Nvidia could acknowledge the RTX 50 Super or lay out its plans while keeping actual release until late 2026. For buyers, this clarity alone may be enough to decide whether to upgrade now or wait a little longer.
AI will take center stage
Even as gamers care about GPUs, AI will remain Nvidia's main focus at CES 2026. The company is expected to spend a lot of time discussing AI hardware for enterprise and data centers, especially accelerators designed for inference, training, and edge deployment.
CES isn't GTC, but it's increasingly becoming a place where Nvidia shows off how its AI stack is scaling, from massive data centers to local AI-powered PCs.
The automotive industry is another likely focus. Nvidia has been deep into autonomous driving and automotive artificial intelligence platforms for years, and CES has traditionally been a place where automakers and chipmakers coordinate their plans. New announcements about DRIVE platforms, AI-powered on-board computers, or expanded partnerships wouldn't be surprising.
In addition to automobiles, Nvidia may also touch upon embedded systems, industrial artificial intelligence, robotics and edge computing. These are areas where Nvidia's hardware and software platforms already dominate, and CES provides the right platform to show how this technology is making its way into everyday products.
Wild Card Hands
One of the most intriguing rumors ahead of CES 2026 involves Nvidia's first major Arm-based PC SoC. codenamed N1x. While the Green team has remained tight-lipped, reports that surfaced earlier this year suggest that the chip could be much more ambitious than originally thought.
According to a specific leak, the N1x could have the same number of GPU cores as the RTX 5070, but integrated directly into the SoC rather than existing as a discrete GPU. If true, it would put the N1x in uncharted territory for integrated graphics, with performance reportedly significantly superior to any other iGPU currently on the market.
The significance here is significant. Instead of positioning the N1x as a low-power ARM experiment, Nvidia could create a high-performance PC AI chip aimed at gaming, content creation, and local AI workloads without a discrete GPU. This fits neatly into Nvidia's broader push towards artificial intelligence computing, where neural loads, inference and acceleration matter as much as traditional raster performance.
While CES would be an ideal place for Nvidia to show off such a platform, don't expect a full product launch or ready-to-sell devices right away. Conceptual opening dedicated to the next generation “PC with artificial intelligence” Windows on ARM premium systems or embedded platforms seem much more likely. Nvidia could have emphasized efficiency, AI throughput, and graphics leadership without positioning the N1x directly as an x86 replacement.
If at least some of the rumors are true, the N1x will not only challenge existing ARM laptop chips, primarily from Qualcomm, but could completely blur the line between integrated and discrete graphics.
