FSR 4 AI upscaling isn't coming to current gaming handhelds or Ryzen AI devices

With the arrival of RDNA and the Radeon RX 9000 Series of graphics cards, one of the standout features was FSR 4 (now called FSR Upscaling (ML)), an AI-based Super Resolution solution that helped level the playing field with NVIDIA DLSS.

3

The only drawback is that FSR 4 and the new FSR Redstone suite of AI technologies are exclusive to the RDNA 4 lineup of desktop Radeon graphics. With AMD's presence and dominance in portable PC gaming, thanks to handhelds like the Steam Deck and ROG Xbox Ally X, an AI upscaling solution like FSR would be a game-changer for image fidelity and performance.

Even when it comes to the newly announced Ryzen AI 400 Series of processors, which feature integrated Radeon graphics powerful enough to game with, because that's RDNA 3.5 and not RDNA 4, there's no FSR 4 AI upscaling. At CES 2026, we spoke to David McAfee, the Vice President and General Manager of Ryzen CPUs and Radeon graphics at AMD, to ask whether FSR Upscaling (ML) would be coming to mobile hardware and to previous-generation Radeon GPUs.

• Read more: AMD's FSR 3 and FSR 4 are now both called FSR Upscaling, but there's a catch
• Read more: AMD FSR Redstone is here, AI-powered Upscaling and Frame Generation for RDNA 4
• Read more: AMD FSR SDK 2.1 with FSR Redstone technology available now for developers

"When we introduced FSR 4, the models that we built were tuned for and optimised for the ML operations that are in the RDNA 4 architecture," David McAfee tells us. "For mobile gaming platforms, it is highly valuable, and we recognise that. We absolutely see that. [AI Upscaling] is a capability that would absolutely add to the gaming experience."

3

"The technical challenge is bringing those models back to older-generation hardware that doesn't have the ML ops, doesn't have the TOPS, and doesn't have the AI throughput to deliver an upscaling experience that meets the quality bar that needs to be met," David McAfee continues. "At the end of the day, we've got to make sure that whatever we do, let's call it augmented gaming experiences, it has to be a high fidelity experience. It has to deliver near native quality. Doing that on older hardware is a very difficult technical challenge for us to solve."

Although we didn't get any indication that AMD was actively looking to port FSR 4 to older Radeon hardware, the "very difficult technical challenge for us to solve" suggests the company could be working on a solution. On the plus side, the new AI-powered FSR for boosting performance and image fidelity is now a core part of AMD's GPU roadmap for all upcoming Radeon products with next-gen or RDNA 4 architecture.

"You'll see, as we advance the architecture forward, understanding the capabilities and needs of these ML algorithms, and how it plays into the graphics architecture itself is a critically important piece of our forward-looking IP roadmap for graphics and how we want to build those products," David McAfee explains.