GPUDesktopReleased Jan 31, 2024

NVIDIA GeForce RTX 4080 SUPER

16 GB GDDR6X · 256-bit · 10,240 cores

A refresh of the RTX 4080 that enables the full AD103 die and faster memory while launching at a lower price than the card it replaced. Aimed at high-refresh 4K gaming, it carries third-generation RT Cores, fourth-generation Tensor Cores with DLSS 3 frame generation, and dual AV1 encoders for streaming and video work.

General

Manufacturer
NVIDIA
Model
GeForce RTX 4080 SUPER
Segment
Desktop
GPU chip
AD103-400
Architecture
Ada Lovelace
Release date
Jan 31, 2024

Memory

Memory size
16 GB
Memory type
GDDR6X
Bus width
256-bit
Bandwidth
736 GB/s
Memory clock
1,438 MHz

Clocks & silicon

GPU clock
2,295 MHz
Boost clock
2,550 MHz
Shader units
10,240 CUDA Cores
Tensor / AI cores
320
RT cores
80
Transistors
45.9 billion
Technology (nm)
5 nm
TSMC 4N (5 nm-class)
TDP / TBP
320 W

Interface & APIs

Bus interface
PCIe 4.0 x16
SLI / multi-GPU
None (no SLI / NVLink)
DirectX
12 Ultimate (12_2)
OpenGL
4.6
Vulkan
1.4
Other APIs
CUDA 8.9, OpenCL 3.0, DLSS 3

AI support

Precisions
FP8FP16BF16INT8INT4TF32FP64
AI accelerator
4th Gen Tensor Cores (320) + 3rd Gen RT Cores (80)
Peak AI TOPS
836 TOPS
Notes
4th-gen Tensor Cores with FP8 Transformer Engine and sparsity. FP64 at 1/64 rate. 836 AI TOPS (FP8, sparsity).
All NVIDIA GPUs →

Desktop gpus from NVIDIA announced around the same time as the NVIDIA GeForce RTX 4080 SUPER. Add any of them to your compare list to see the specs side by side.