NVIDIA GeForce RTX 4080 SUPER GPU Family Specifications

We reviewed the NVIDIA GeForce RTX 4080 SUPER Founders Edition video card, which fixes the pricing of the GeForce RTX 4080 and sets it right, upping the price value quite a bit and value for the performance overall. It's a small performance uplift, and will practically provide the same experience as the GeForce RTX 4080, but the pricing seals the deal on what it offers with its incredible power efficiency, cooling and build overall.

GPU Family Basics
GPU Manufacturer	NVIDIA
GPU Generation	RTX 40 Series
GPU Architecture Name	Ada Lovelace
GPU Die Code	AD103
Default TGP	320 W
Launch Price	$999

GPU Family Memory
Default Memory Bandwidth	736 GB/s
Default Memory Size	16 GB
Memory Bus Width	256 bit
Memory Type	GDDR6X

GPU Family Chip Details
Transistors	45.9 billion
Die Size	379 mm^2
CUDA Cores	10240
RT Cores	80
ROPs	112
TMUs	320

GPU Family Clock Speeds
Default GPU Base Clock	2295 MHz
Default GPU Boost Clock	2550 MHz
Default Memory Clock	23 GHz

The GeForce RTX 4080 SUPER is based on the same Ada Lovelace AD103 die as the GeForce RTX 4080, but now contains the full specifications, or full die, of AD103. You will find that the SM count increases, and the CUDA core count has been increased, along with all other subsequent RT cores and Tensor Cores. It also has 16GB of GDDR6X similar to the RTX 4080, but the memory speed has been increased to provide even more memory bandwidth at 736GB/s. Remarkably, the TGP remains the same as the RTX 4080 at just 320W. It also has the same RTX features and AV1 encoders.

The GeForce RTX 4080 SUPER has 80 SMs and 10,240 CUDA Cores which gives it 80 RT Cores and 320 Tensor Cores, 320 Texture Units, and 112 ROPs. The base clock is 2295MHz while the Boost Clock is 2550MHz. It has 65536K of L2 cache. It has 16GB of GDDDR6 at 23Gbps on a 256-bit memory bus giving it 736GB/s of memory bandwidth. The TGP is 320W.