NVIDIA's long-rumored GeForce RTX 50 SUPER graphics cards have been shipped to the company's board partners, but we can't get our hands on them just yet. According to VideoCardz, NVIDIA's board partners have already received the GeForce RTX 50 SUPER silicon, but the release is on hold by Team Green headquarters. This means that while the GPUs are physically with the board partners, they can't proceed with the launch due to a shortage of GDDR7 memory chips. It was previously rumored that the "SUPER" series was planned to feature denser GDDR7 memory modules, offering 3 GB of capacity per chip, which would increase the memory configuration of the standard GeForce RTX 5070, RTX 5070 Ti, and RTX 5080. Initially, the RTX 5070 SUPER was expected to be upgraded to offer 18 GB, while the RTX 5070 Ti SUPER and RTX 5080 SUPER would each provide 24 GB of GDDR7 memory.

Meanwhile, all other specifications will remain the same. However, since the 3 GB GDDR7 memory modules are being used in other products like NVIDIA's AI GPU portfolio, including the RTX PRO 6000 "Blackwell" and "Rubin CPX," the company has likely decided to prioritize this high-margin business. The availability of 3 GB GDDR7 modules is much lower than the current industry demand. As a result, gamers are left with the regular GeForce RTX 50 series for now, which uses the more readily available 2 GB GDDR7 memory modules.

Previous rumors indicated that NVIDIA had seemingly indefinitely postponed the launch of the GeForce RTX 50 Super-series GPUs, with no real indication of a launch date for new Super cards in sight. With the recent apparent cancellation of the RTX 5050 9 GB GPU and RTX 60-series GPUs on the cards for late 2027, it seemed more and more unlikely that the RTX 50 Super-series GPUs would ever launch at all. Now, thanks to listings in the online Seasonic PSU calculator, rumors of upcoming RTX 50 Super GPUs are floating around. If the Seasonic calculator is anything to go by, it looks as though the RTX 50 Super cards will initially be available in three variants: RTX 5080 Super, 5070 Ti Super, and an RTX 5070 Super. There is no indication of an RTX 5060 Super just yet.

According to information in the PSU calculator, the RTX 5080 Super will have a TGP of 415 W, which is a 55 W increase over the RTX 5080's 360 W as reported by the same Seasonic PSU calculator. Similarly, the RTX 5070 Ti Super will get a 50 W increase over the 5070 Ti's 300 W, for a TGP of 350 W, while the RTX 5070 Super is rated at 275 W, compared to the 250 W of the original RTX 5070. This is a more substantial increase than the 15-20 W increase that came with the jump from the RTX 4070, 4070 Ti, and 4080 to their respective Super variants. Of course, previously, NVIDIA's Super variants also came with additional Cuda, RT, and Tensor cores as well as faster memory, all of which may result in higher power draw to sustain the same or similar GPU clock speeds.

Artificial Intelligence may be eating the world of software now, but gamers are suffering. According to The Information, NVIDIA has reportedly entirely postponed the launch of its GeForce RTX 50 "SUPER" refresh, as the company's executives are prioritizing AI accelerators over the gaming sector, which consumes precious cutting edge GDDR7 memory. The GeForce RTX 50 "SUPER" refresh was originally scheduled for an announcement at CES 2026, with shipping in Q1 or Q2 of 2026. However, the GDDR7 memory used in the SUPER lineup was a high-capacity 3 GB version, which NVIDIA managers in December deemed too important for gamers, postponing the refresh entirely.

The "SUPER" series was planned with denser GDDR7 memory modules, offering 3 GB of capacity per chip, increasing the memory configuration of the standard GeForce RTX 5070, RTX 5070 Ti, and RTX 5080. Initially, the RTX 5070 SUPER was planned with an upgrade to offer 18 GB, while the RTX 5070 Ti SUPER and RTX 5080 SUPER would each provide 24 GB of GDDR7 memory. As NVIDIA's AI GPU portfolio also uses the high-density GDDR7 memory, like the RTX PRO 6000 "Blackwell" and "Rubin CPX" the company has decided to instead prioritize this high-margin business, leaving gamers with inflated prices of the regular GeForce RTX 50-series.

As the Consumer Electronics Show of 2026 comes to an end, our field crew has done of a lot of work to keep readers updated. However, pre-CES expectations were high for several product launches, that sadly didn't happen. In today's piece we are ranking the top five things we didn't get at CES 2026, even with hopes of a product launch occurring during the show.

1) First on our non-weighted ranking is NVIDIA's GeForce RTX 50-series "Blackwell" SUPER refresh. This mid-cycle was originally planned for late Q1 to early Q2 2026, with a possible announcement at CES 2026. The "SUPER" treatment was planned with denser GDDR7 memory modules with 3 GB of capacity per chip, increasing the memory configuration of the standard GeForce RTX 5070, RTX 5070 Ti, and RTX 5080. Initially, the RTX 5070 SUPER was planned with an upgrade to offer 18 GB, while the RTX 5070 Ti SUPER and RTX 5080 SUPER would each provide 24 GB of GDDR7 memory.

According to multiple sources from Hong Kong and Taiwan, NVIDIA's upcoming mid-cycle refresh of the "Blackwell" SUPER GPU series is not canceled, although add-in card partners are still awaiting final specifications. HKEPC reports: "NVIDIA informed AIC yesterday that the RTX 50 SUPER plan is not canceled but the release date has been postponed to Q3 2026. The statement by Uniko's Hardware is incorrect." We previously reported on the rumor from Uniko's Hardware that the current DRAM shortage could affect the planned release date and potentially lead to the cancellation of the entire rollout. These GPUs are expected to feature more dense GDDR7 memory modules with 3 GB per module, and it was believed that NVIDIA held most of the stock for AI applications. However, this has now been proven false.

Interesting information comes from Benchlife, a source with a strong track record on NVIDIA news. They confirm that the RTX 50-series SUPER GPUs are not canceled, but NVIDIA has reportedly not provided AICs with the final specifications yet. "As we reported earlier, NVIDIA has yet to provide design information for the GeForce RTX 50 SUPER series. As of November, no AIC has received any design details. Without this information, any talk of cancellation or postponement is just nonsense," claims Benchlife.

NVIDIA is planning to update its GeForce RTX 50-series SUPER line of graphics cards by Christmas 2025, says a report by TweakTown. The company will look to bolster the memory sizes of key performance-segment and high-end graphics card SKUs in a bit to boost their performance in higher resolutions, particularly with ray tracing and neural rendering enabled. In particular, NVIDIA is expected to leverage new 24 Gbit density GDDR7 memory chips that allow it to create memory sizes such as 18 GB over a 192-bit wide memory bus, or 24 GB across a 256-bit wide memory bus. Besides the added memory, NVIDIA is expected to marginally increase shader counts and GPU clock speeds.

The TweakTown article also sheds light on possible specs of the RTX 50-series SUPER lineup. Only the RTX 5070 SUPER sees an increase in SM counts over its non-SUPER predecessor, with the card maxing out the "GB205" silicon, enabling all 50 SM, for 6,400 CUDA cores, 200 Tensor cores, and 50 RT cores. The RTX 5070 Ti SUPER sees no increase in SM count over the RTX 5070 Ti despite being based on the "GB203" chip that the two share with the RTX 5080, and there being a rather large gap in SM count between the two (70 vs. 84). The RTX 5080 SUPER, much like the RTX 5080, maxes out the "GB203." What the RTX 5070 Ti SUPER and RTX 5080 SUPER have going for them is a 50% increase in memory size to 24 GB. The RTX 5070 Ti SUPER holds onto the same 28 Gbps memory speed as RTX 5070 Ti, while the RTX 5080 SUPER gets a marginal increase in speed to 32 Gbps. There are fairly good increases in TGP across the board for the RTX 50-series SUPER.

NVIDIA will tap into 24 Gbit (3 GB) GDDR7 memory chips and increase memory sizes across the board for its RTX 50-series SUPER line of GPUs slated for later this year, if leaked specs of the upcoming GeForce RTX 5070 SUPER are anything to go by. Kopite7kimi, a reliable source with NVIDIA leaks, says that the RTX 5070 SUPER will feature 18 GB of memory—that's six 24 Gbit memory chips across a 192-bit wide GDDR7 memory bus. The card has a SKU designation of "PG147-SKU65" and ASIC code of "GB205-400-A1."

Besides 18 GB of memory, the RTX 5070 SUPER reportedly maxes out the "GB205" silicon it's based on, enabling all 50 SM present. The current RTX 5070 has 48 out of 50 SM enabled for 6,144 CUDA cores, whereas the RTX 5070 SUPER, with its 50 SM, should have 6,400 CUDA cores. The marginal increase in shader count will be bolstered by the 50% increase in memory size, and possible increases in GPU boost speeds. The memory bandwidth, however, remains unchanged. It ticks at the same 28 Gbps as on the RTX 5070, which yields 672 GB/s. The TGP will be increased to 275 W, from 250 W.