RTX 4070 Super Will Feature a Full Fat 48MB L2 Cache on AD104 Chip

4070 super surfaces

NVIDIA has confirmed that the upcoming GeForce RTX 4070 SUPER GPU will be equipped with a full 48 MB L2 cache for AD104 chips. This is a significant upgrade from the previous RTX 4070, which was listed with a 36 MB L2 cache.

Keep a lookout for the 4070 Ti 12GB Price Drops.

The NVIDIA GeForce RTX 4070 and the RTX 4070 SUPER are both powerful GPUs, but they have some key differences that set them apart.

The RTX 4070 is a strong performer in its own right, equipped with a 36 MB L2 cache and an AD104 chip. It’s designed for high-refresh-rate 1080p and 1440p gaming, and it’s capable of delivering impressive performance in a wide range of games. However, in certain scenarios where the memory can become strained, such as with higher-resolution textures and resolutions, the RTX 4070 can experience slow-downs in gaming.

Initially, the RX 7800 XT was seen as a direct competitor to the RTX 4070. However, upon closer examination, these two GPUs exhibit distinct differences in both price and performance.

The RX 7800 XT, with its raw horsepower, is indeed a compelling option. It boasts 16GB of GDDR6 memory, which surpasses the 12GB GDDR6X memory of the RTX 4070 SUPER. Despite this advantage, the memory speed of the 7800 XT falls short when compared to the RTX 4070 SUPER, at least in pen and paper.

However, the RX 7800 XT does have a higher power draw, which is a crucial factor for many users. This is where the RTX 4070 SUPER existence starts to make more sense.

RTX 4070 Super – Specs and Benchmarks Update

NVIDIA has confirmed that the upcoming GeForce RTX 4070 SUPER GPU will be equipped with a full 48 MB L2 cache for AD104 chips1. This is a significant upgrade from the previous RTX 4070, which was listed with a 36 MB L2 cache.

The RTX 4070 SUPER will feature either the AD104-350 or AD103-175 GPU configurations, both of which will have the same 7,168 cores. The GPU will also stick with the 12 GB GDDR6X memory across the same 192-bit bus interface.

Having a larger L2 cache is crucial for a GPU like the RTX 4070 SUPER, which is designed for high-refresh-rate 1080p and 1440p gaming PCs1. Higher-resolution textures and the resolution itself can lead to bottlenecks within the memory subsystem. While the RTX 4070 SUPER is equipped with the latest G6X memory, there are still certain scenarios where the memory can become strained and cause slow-downs in gaming.

The RTX 4070 SUPER is expected to be around 15% faster than the RTX 4070 Non-SUPER, marking the biggest uplift in the SUPER lineup. The card is also stated to be faster than an RTX 3090 without frame generation, though the performance is going to vary on a game-to-game basis.

Image Source: Nvidia