Nvidia RTX 4070 Ti Super with AD102 graphics processor appears – a novel variant with a reworked RTX 4090 chip appears

Published:

Nvidia GeForce RTX 4070 Ti Super, one of the best graphics cards, will not be the only one of its kind on the market. MSI (via wxkiwa) recently released the RTX 4070 Ti Super 16G Ventus 3X Black OC, which features different silicon than the original RTX 4070 Ti Super.

Nvidia was the first to ship the RTX 4070 Ti Super with AD103 silicon, the same chip used in the RTX 4080 and RTX 4080 Super. It’s no surprise that Nvidia uses the same die for multiple GPU variants, as we discussed in our Nvidia Ada Lovelace RTX 40 series review. However, renders of MSI’s latest custom RTX 4070 Ti Super card show that the graphics card has a different die . The capacitor arrangement between the RTX 4070 Ti Super 16G Ventus 3X Black OC and the previously released RTX 4070 Ti Super 16G Ventus 3X OC looks different. The former has four SP-Caps and two MLCC clusters, while the latter has only three SP-Caps, which means switching to different silicon.

- Advertisement -

The AD103 chip of the RTX 4070 Ti Super card supports 66 SM modules out of 80 available on the matrix. The configuration provides 8,448 CUDA cores and has four 64-bit memory interfaces enabled. The only other potential Nvidia silicon would be a move to the larger AD102 – the AD104 used in the base RTX 4070 Ti doesn’t have enough memory or SM controllers. On the other hand, the AD102 silicon contains 144 SM modules (18,432 CUDA cores) and six 64-bit memory controllers. This means that the “new” GeForce RTX 4070 Ti Super only supports 45.8% of the SM AD102 modules, which is less than half of what it potentially offers – along with 66.7% of the memory interfaces.

The move from AD103 to AD103 silicon in the 4070 Ti Super is likely due to the desire to exploit chips that do not meet the requirements of other, more powerful GPUs. Performance always varies, and over time Nvidia has likely acquired some AD102 chips that can’t even meet the requirements of the RTX 4080 Super. However, a change in silicon will typically not benefit the consumer.

The specifications and performance of the RTX 4070 Ti Super remain the same. For example, MSI’s GeForce RTX 4070 Ti Super 16G Ventus 3X Black OC has the same boost clock of 2655 MHz as the GeForce RTX 4070 Ti Super 16G Ventus 3X OC. Power consumption varies slightly, at least on paper, although without in-depth testing we wouldn’t want to draw any firm conclusions.

RTX 4070 Ti Super 16G Ventus 3X Black OC (295 W) has 10 W more power consumption than RTX 4070 Ti Super 16G Ventus 3X OC. It seems that the larger AD102 matrix draws a bit more power, or maybe MSI just wants to give the newer variant a bit more headroom. Regardless, the RTX 4070 Ti Super still comes with a 16-pin power connector, and the extra 10W isn’t something consumers should worry about. This isn’t a concern on the power supply side either, as MSI still recommends a minimum 700W unit for its GeForce RTX 4070 Ti Super 16G Ventus 3X Black OC card.

(Image source: wxnod/X)

The GeForce RTX 4070 Ti Super AD102 allows Nvidia to maximize silicon performance. Poorly performing AD102 silicon that doesn’t qualify for, say, the GeForce RTX 4080 Super (the original RTX 4080 has been discontinued) could be used in the RTX 4070 Ti Super. This isn’t the first time Nvidia has used this tactic, and the manufacturer isn’t the only one doing it.

There’s no way to re-enable any of the disabled SMs and hasn’t been for many years, so you still get the same basic specs. In addition to more SMs, AD102 silicon also has more NVENC and NVDEC blocks for video processing, but additional units can also be connected. This likely marks the final round of Ada Lovelace silicon removal, as we expect Nvidia Blackwell RTX 50-series GPUs to hit the market in just a few months.

Related articles