60%
Plausible
NVIDIA's GeForce RTX 50 SUPER GPUs have reportedly been pushed back to Q3 2026 following the recent DRAM shortage situation.
NVIDIA GeForce RTX 50 GPUs Have Not Been Cancelled, But Pushed Back To Q3 2026
Earlier, we had reported that NVIDIA's GeForce RTX 50 SUPER GPUs have been delayed due to the ongoing DRAM shortages, particularly related to the 3 GB GDDR7 modules, which are going to be featured on the refreshed lineup. The rumor also stated that the lineup might have been cancelled; however, that isn't the case.
According to Insider, MegaSizeGPU, it looks like the NVIDIA GeForce RTX 50 SUPER GPUs are still in plans. The initial plan was to introduce the GPUs in Q1 2026, which matches our report, but that has changed to Q3 2026. NVIDIA could likely unveil the series around Computex 2026, with a retail launch in Q3 2026. However, gamers won't have to wait that long to experience Blackwell, with RTX 5080 servers soon to go live on GeForce NOW. Just like before, NVIDIA is expected to introduce three SUPER GPUs:
These refreshed GPUs, which include the GeForce RTX 5080 SUPER, RTX 5070 Ti SUPER, and the RTX 5070 SUPER, were expected to feature 3 GB GDDR7 memory dies, however, high prices and shortages may have led NVIDIA to postpone the launch and focus on products with higher margins such as the RTX PRO 6000 Blackwell GPUs which feature up to 96 GB VRAM using the same 3 GB dies or the RTX 5090 Laptop GPU which also leverages 3 GB dies for up to 24 GB VRAM across a 256-bit bus.
As per earlier reports, NVIDIA had planned the GeForce RTX 50 SUPER GPU series for Q1-Q2 2026, with a possible unveil at CES 2026 or at a special GeForce event. The company didn't announce any SUPER GPUs officially, but there have been various leaks. We also confirmed with our own sources that NVIDIA wasn't planning to launch RTX 50 SUPER GPUs anytime this year, and all plans point to a 2026 launch.
While NVIDIA's current lineup doesn't face any challenge from the opposition (Radeon RX 9000) series, users have been demanding higher VRAM models, and that is exactly what the GeForce RTX 50 SUPER family is going to be. The RTX 5080 SUPER would've offered up to 24 GB VRAM, the 5070 Ti would've offered up to 24 GB VRAM too, and the RTX 5070 SUPER would've offered 18 GB VRAM.
This 50% VRAM boost would make the cards look very enticing, but right now, NVIDIA may not be able to keep the prices in control or equivalent to their Non-SUPER variants due to rising DRAM costs. With all of this said, NVIDIA's GeForce RTX 50 SUPER GPUs will be a solid refresh before the next-gen Rubin gaming lineup, which is expected in 2027.
NVIDIA RTX 50 SUPER GPU Lineup (Preliminary):
| Graphics Card Name | NVIDIA GeForce RTX 5080 SUPER | NVIDIA GeForce RTX 5080 | NVIDIA GeForce RTX 5070 Ti SUPER | NVIDIA GeForce RTX 5070 Ti | NVIDIA GeForce RTX 5070 SUPER | NVIDIA GeForce RTX 5070 |
|---|---|---|---|---|---|---|
| GPU Name | Blackwell GB203-450 | Blackwell GB203-400 | Blackwell GB203-350 | Blackwell GB203-300 | Blackwell GB205-400 | Blackwell GB205-300-A1 |
| GPU SMs | 84 (84 Full) | 84 (84 Full) | 70 (70 Full) | 70 (70 Full) | 50 (50 Full) | 48 (50 Full) |
| GPU Cores | 10752 | 10752 | 8960 | 8960 | 6400 | 6144 |
| Clock Speeds | TBD | 2.62 GHz | TBD | 2.42 GHz | TBD | 2.51 GHz |
| Memory Capacity | 24 GB GDDR7 | 16 GB GDDR7 | 24 GB GDDR7 | 16 GB GDDR7 | 18 GB GDDR7 | 12 GB GDDR7 |
| Memory Bus | 256-bit | 256-bit | 256-bit | 256-bit | 192-bit | 192-bit |
| Memory Speed | 32 Gbps | 30 Gbps | 28 Gbps | 28 Gbps | 28 Gbps | 28 Gbps |
| Bandwidth | 1024 GB/s | 960 GB/s | 896 GB/s | 896 GB/s | 672 GB/s | 672 GB/s |
| Power Interface | 1 12V-2x6 (16-Pin) | 1 12V-2x6 (16-Pin) | 1 12V-2x6 (16-Pin) | 1 12V-2x6 (16-Pin) | 1 12VHPWR (16-Pin) | 1 12VHPWR (16-Pin) |
| Launch | TBD | 30th January, 2025 | TBD | 20th February, 2025 | TBD | 5th March, 2025 |
| TBP | 400W+ | 360W | 350W | 300W | 275W | 250W |
| Price | TBD | $999 US | TBD | $749 US | TBD | $549 US |
Follow Wccftech on Google to get more of our news coverage in your feeds.
