NVIDIA Scrubs GeForce RTX 4080 12GB Released; 16GB will be the only RTX 4080 card.

In a short post posted on NVIDIA’s website today, the company announced that it was “unreleased” the planned GeForce RTX 4080 12GB card. The lowest of the initially announced RTX 40-series cards, the RTX 4080 12GB received considerable criticism after announcing that it would fork the 4080 tier between the two cards that don’t even share a common GPU. As if succumbing to the pressure of these complaints, NVIDIA removed the card from its RTX 40-series lineup and canceled its November launch. Here’s NVIDIA’s brief message: The RTX 4080 12GB is a fantastic graphics card, but the name is incorrect. Having two GPUs designated as 4080 is confusing, so I’m holding the “unlaunch” button on the 4080 12GB. The RTX 4080 16GB is amazing and is set to entertain gamers everywhere on November 16th. NVIDIA currently does not provide details on future plans for AD104 based video cards. However, given the circumstances, it is currently a reasonable assumption that NVIDIA plans to release it with a different part number in the future. NVIDIA GEFORCE SPECIAL COMPARISON RTX 4090 RTX 4080 16GB RTX 4080 12GB (CANCEL) CUDA CORES 16384 9728 7680 ROPS 176 112 80 Boost Clock 2520MHZ 2520MHz 2520MZ 2610MZ 21GBPS GDDR6X 22.4GBPS GDDR6X GDDR6X VRAM B 24G 82.6 TFLOPS 48.7 TFLOPS Performance (TFLOPS GDDR6X VRAM B 24G 82.6 TFLOPS) 330 TFLOPS 195 TFLOPS 160 TFLOPS Tensor Performance (FP8) 660 TFLOPS 390 TFLOPS 321 TFLOPS TDP 450W 320W 285W L2 Cache 72MB 64MB 48MB GPU AD102 AD103 AD104 Transistor Count 76.3B Architecture 45.9B Adalac1TS Love Adalac4/Love AMC Release 2022/11/16/ 2022 Never Launch Price MSRP: $1599 MSRP: $1199 Previous: $899 Looking at the card specs, it’s easy to see why NVIDIA’s core-based enthusiast gamers aren’t happy. The two RTX 4080 parts shared a common architecture, but not a common GPU. But for that matter, it’s typical performance. The RTX 4080 12GB would have been based on the smaller AD104 GPU rather than the AD103 GPU used in the 16GB model as is. In practice, this would have caused the 12GB model to provide only about 82% of the former’s shader/tensor throughput and 70% of its memory bandwidth. Significant performance gap, confirmed by NVIDIA’s own figures prior to launch. NVIDIA is no stranger to overloading their product lines in this way. Similar-named parts offer unequal performance, the difference is only indicated by the amount of VRAM. This was the practice starting with the GTX 1060 series and continuing to the RTX 3080 series. However, the performance gap between the RTX 4080 parts is much larger than what NVIDIA has done before, giving more attention to the problems caused by these disparate parts sharing a common product name. NVIDIA’s decision to sell the AD104 part as an RTX 4080 card from the start was equally criticized. Traditionally, the next card under the xx80 card in NVIDIA’s product stack is a kind of xx70 card. The video card names and GPU identifiers are arbitrary in nature, but NVIDIA’s initial performance figures are very similar to the kind of card that most people expect from the RTX 4070, with 20% more (or more) better behind the RTX 4080, and the last generation. Equivalent to the flagship RTX 3090 Ti. In other words, there was considerable suspicion within the enthusiast community that NVIDIA offered a higher price while attempting to sell the RTX 4070 as the RTX 4080. In any case, these plans are now officially discontinued. Whatever NVIDIA has planned for their AD104 based RTX 40 series cards, only the company knows for now. Meanwhile, on November 16, when the RTX 4080 series launches, only 16GB AD103 based cards will be available, with prices starting at $1199.
#NVIDIA #Scrubs #GeForce #RTX #12GB #Released #16GB #RTX #card

Leave a Comment

Your email address will not be published. Required fields are marked *