NVIDIA GeForce RTX 4080 GPU Family Specifications

We reviewed the NVIDIA GeForce RTX 4080 Founders Edition video card and put it through its paces, pushing 4K, 1440p, Ray Tracing, and DLSS. Performance exceeded the previous generation. 4K with Ray Tracing and the uplift versus the GeForce RTX 3080 felt a bit underwhelming for the price point. The step-down in performance compared to the GeForce RTX 4090 seems unbalanced for the price difference. The build and cooling are exceptional, with a robust video card that stays quiet, and cool and is also power efficient for the performance delivered. The GeForce RTX 4080 Founders Edition is a good video card that is otherwise marred by its high price tag for the performance offered and price-to-performance value proposition versus the GeForce RTX 4090.

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	$1,199

GPU Family Memory
Default Memory Bandwidth	716.8 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
CUDA Cores	9728
RT Cores	76
ROPs	112
TMUs	302

GPU Family Clock Speeds
Default GPU Base Clock
Default GPU Boost Clock	2505 MHz
Default Memory Clock	22.4 GHz

The GeForce RTX 4080 is based on NVIDIA’s new Ada Lovelace architecture, built on a custom NVIDIA TSMC 4N process and based on the AD103 GPU. There are many new innovations in Ada Lovelace GPUs, which include improved Ray Tracing, improved Tensor Cores, Shader Execution Reordering, Displaced Micro-Meshes, Opacity Micro-Masks, FP8 Inferencing, improved Optical Flow Accelerator and DLSS 3 with Frame Generation. This adds onto additional features such as NVIDIA Reflex, NVIDIA RTX Remix, NVIDIA Broadcast, NVIDIA Studio, and NVIDIA Omniverse. For a more complete description of these new features and architecture, check out our GeForce RTX 4090 Review.