For now, Nvidia’s GeForce RTX 4090 graphics card comfortably sits on high of our GPU hierarchy, however as ever, the corporate is tough at work to supply one thing much more highly effective — a seemingly inevitable GeForce RTX 4090 Ti graphics card. In accordance with famend {hardware} leaker @kopite7kimi, this product will use the AD102 graphics processor in a virtually full configuration, and it’ll devour as much as 600W of energy.
In accordance with tweeted particulars, the Nvidia’s GeForce RTX 4090 Ti mannequin PG136/139-SKU310 options AD102 GPU with 18,176 CUDA cores, a 96M L2cache and a 384-bit reminiscence bus. In contrast to the skilled and datacenter-oriented RTX 6000 Ada Technology graphics card with 48GB of reminiscence — which makes use of the AD102 in an identical configuration — the product aimed toward avid gamers and prosumers will ‘solely’ carry 24GB of GDDR6X reminiscence, with a 24 GT/s knowledge switch velocity, which is sufficient for all video games, at the very least for now.
GPU | FP32 CUDA Cores | Reminiscence Configuration | TBP | MSRP | |
GeForce RTX 4090 Ti | AD102 | 18176 (?) | 24GB 384-bit 24 GT/s GDDR6X (?) | 600W (?) | ? |
GeForce RTX 4090 | AD102 | 16384 | 24GB 384-bit 21 GT/s GDDR6X | 450W | $1,599 |
GeForce RTX 4080 | AD103 | 9728 | 16GB 256-bit 22.4 GT/s GDDR6X | 320W | $1,199 |
GeForce RTX 4070 Ti | AD104 | 7680 | 12GB 192-bit 21 GT/s GDDR6X | 285W | $799 |
GeForce RTX 4070 | AD104 | 5888 (?) | 12GB 192-bit 21 GT/s GDDR6X | 250W (?) | ? |
GeForce RTX 4060 Ti | AD106 | 4352 (?) | 8GB 128-bit 18 GT/s GDDR6 | 160W (?) | <$500? |
GeForce RTX 3070 | GA104 | 5888 | 8GB 256-bit 14 GT/s GDDR6 | 220W | $499 |
Energy consumption of the brand new flagship graphics card from Nvidia might be as much as 600W, in accordance with the leaker, so anticipate it to characteristic a particularly refined cooling system. In reality, it’s logical to anticipate at the very least a few of Nvidia’s board companions to ship their GeForce RTX 4090 Ti variations with hybrid closed-loop cooling methods.
Word that the AD102 GPU has 18,432 CUDA cores in whole, so the GeForce RTX 4090 Ti will use virtually all of them. For the time being, we’re uncertain whether or not Nvidia plans to ever use AD102 with all of its stream processors enabled, because it’s probably robust to search out sufficient good GPUs with all cores working correctly at excessive clock speeds.
It additionally stays to be seen how a lot Nvidia will cost for the GeForce RTX 4090 Ti. Take into account that the GeForce RTX 4090 is at the moment the world’s finest graphics card for gaming, and that has no direct rivals. So it is very probably that the GeForce RTX 4090 Ti might be dearer than the present flagship (which frequently sells for greater than $2,000). We are able to solely surprise how a lot will the Titanium variant is ready to price. However except you are an expert consumer who can use a card like this rather than a a lot pricier choice just like the RTX 6000, it is unlikely you will discover the RTX 4090 Ti’s road value all that interesting.