Although something has to be formally announced with a timeline for it to be delayed, the latest word from renowned hardware leaker @hongxing2020 on X is reporting that NVIDIA's upcoming GeForce RTX 50 Series SUPER refresh has been delayed, suggesting that the potential Q4 2025 holiday release we recently reported on for the latest SUPER cards is no longer happening.
This implies that the refresh, which includes the GeForce RTX 5070 SUPER, RTX 5070 Ti SUPER, and RTX 5080 SUPER, is on track for a 2026 release, with CES 2026 being the likely time and place for a formal announcement and reveal. Although we'll need to wait, we've already been made aware of the specifications of the GeForce RTX 50 Series SUPER refresh thanks to various insider reports. One of the reasons for the delay could be related to the GPUs using newer 3GB GDDR7 modules.
The key takeaway from NVIDIA's latest SUPER GPUs is that they will all feature a significant 50% increase in GDDR7 memory capacity, making them better suited for high-resolution gaming and more intensive AI workloads. Outside of this performance, the new GeForce RTX 50 Series lineup is expected to be broadly similar to the existing GeForce RTX 50 Series cards, unless the increased power limit results in a significant increase in Boost Clock speeds.
- Read more: GeForce RTX 50 SUPER Series refresh could arrive later in 2026 than expected
- Read more: GeForce RTX 50 SUPER Series on track for a holiday 2025 release
- Read more: GeForce RTX 5080 SUPER specs reveal it's going to be a 415W GPU

Outside of the GeForce RTX 5070 SUPER, which features a slight increase in CUDA Core count, the only real difference between the SUPER and non-SUPER GPUs is the increase in VRAM and memory speed. However, as we've seen with the current RTX 50 Series lineup, even a modest overclock can lead to notable performance gains, so there's a chance that the new super cards could deliver an average 5-10% increase in performance.
Here's a closer look at the current GeForce RTX 50 Series SUPER specs, as rumored, compared to their non-SUPER variants.
| GPU Specs | GeForce RTX 5080 | GeForce RTX 5080 SUPER | GeForce RTX 5070 Ti | GeForce RTX 5070 Ti SUPER | GeForce RTX 5070 | GeForce RTX 5070 SUPER |
|---|---|---|---|---|---|---|
| Architecture | Blackwell | Blackwell | Blackwell | Blackwell | Blackwell | Blackwell |
| Process | TSMC 4N | TSMC 4N | TSMC 4N | TSMC 4N | TSMC 4N | TSMC 4N |
| CUDA Cores | 10752 | 10752 | 8960 | 8960 | 6144 | 6400 |
| Tensor Cores (AI) | 330 (5th Gen) | 330 (5th Gen) | 280 (5th Gen) | 280 (5th Gen) | 192 (5th Gen) | 200 (5th Gen) |
| Ray Tracing Cores | 84 (4th Gen) | 84 (4th Gen) | 70 (4th Gen) | 70 (4th Gen) | 48 (4th Gen) | 50 (4th Gen) |
| GPU Boost Clock | 2617 MHz | TBC | 2452 MHz | TBC | 2512 MHz | TBC |
| Memory | 16GB GDDR7 | 24GB GDDR7 | 16GB GDDR7 | 24GB GDDR7 | 12GB GDDR7 | 18GB GDDR7 |
| Memory Interface | 256 Bit | 256 Bit | 256 Bit | 256 Bit | 192 Bit | 192 Bit |
| Bandwidth | 960 GB/sec | 1024 GB/sec | 896 GB/sec | 896 GB/sec | 672 GB/sec | 672 GB/sec |
| TGP | 360W | 415W | 300W | 350W | 250W | 275W |




