NVIDIA’s GeForce RTX 3090 Ti was originally supposed to launch late last month, but production issues have delayed the release indefinitely. This is something you don’t normally see with a top-of-the-line SKU which begs the question why the company decided to announce a full-fat die GPU so late into the product cycle. Igor’s Lab may just have the answer to that question.
According to the German outlet, NVIDIA designed the RTX 3090 Ti as a playground for AICs to prepare for the upcoming RTX 4070, 4080, and 4090 graphics cards. Based on the Ada Lovelace microarchitecture, these GPUs will leverage TSMC’s 5nm process node, and double the ALU count to over 16K FP32 shaders. This will come at the cost of significantly increased power draw.
The GeForce RTX 3090 Ti which has a default TBP of 450W is designed to have a maximum power limit of 520W. Going by these numbers, it’d be safe to assume that the RTX 4080, and 4090 will also have a TBP of around 450W, with factory overclocked variants pushing the 500W mark. That’s a bit below the 600W limit of the 12VHPWR power connector but considering safety standards it’s high enough.
Another aspect worth discussing is the 21Gbps GDDR6X memory slated to be paired with the RTX 3090 Ti. According to Igor, despite featuring the fastest chips from Micron, these memory dies are going to have trouble meeting the lofty mark. With 18Gbps GDDR6 modules from Micron already being paired with AMD’s RDNA 2 refresh, NVIDIA is almost certainly going to pair its higher-end RTX 40 series SKUs, most notably the RTX 4080, 4090 with faster 21 Gbps GDDR6X chips.