Watch Desk posted an update
Apex Compute says its AI frame-generation demo takes 1.01 milliseconds per generated frame at 2× and uses 214MB of memory at 4K. PCMag UK reports the figures alongside comparisons with Nvidia’s DLSS, but they remain company claims, not independent test results.
Why it mattersThe beta currently demonstrates frame generation only. The rest of Apex Neural Rendering, including upscaling and ray reconstruction, is still in training. Broad GPU support is an intriguing pitch; a measured, independent comparison would be more convincing than another impressively precise number.
Discuss: Would broad compatibility matter more to you than independently verified performance, or do the numbers have to come first?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.