NVIDIA GeForce RTX 4080 SUPER: Specs, Key Features & Rivals

The RTX 4080 Super is how NVIDIA approaches the high-end graphics card class. Direct alternatives to the RTX 4080 Super include RTX 5080, RX 7900 XTX and RX 7900 XT.

VRAM16 GB
Shader units10,240
Boost clock2,550 MHz
Memory bandwidth736 GB/s
Total board power320 W
Launch price (MSRP)$999

Summarize this page with AI:

ChatGPT Claude Gemini

Key Specifications

GPU & Performance

GPU & Performance: NVIDIA GeForce RTX 4080 SUPER
Architecture	Ada Lovelace
GPU die	AD103
Process	TSMC 4N
Shader units	10,240
Ray tracing units	80
Base clock	2,295 MHz
Boost clock	2,550 MHz
FP32 computeTheoretical peak; AMD counts dual-issue, so compare within a brand only	52.2 TFLOPS

Memory

Memory: NVIDIA GeForce RTX 4080 SUPER
VRAM	16 GB
Memory type	GDDR6X
Memory bus	256-bit
Memory bandwidth	736 GB/s

Features

Features: NVIDIA GeForce RTX 4080 SUPER
Upscaling	DLSS Super Resolution
Frame generation	DLSS Frame Generation (2x)
PCIe interface	PCIe 4.0 x16

Power & Thermals

Power & Thermals: NVIDIA GeForce RTX 4080 SUPER
Total board power	320 W
Recommended PSU	750 W
Power connector	1x 16-pin (12VHPWR)

Size & Connectivity

Size & Connectivity: NVIDIA GeForce RTX 4080 SUPER
Reference card length	11.97 in
Slot width	3 slots
Display outputs	3x DisplayPort 1.4a, 1x HDMI 2.1

Price

Price: NVIDIA GeForce RTX 4080 SUPER
Launch price (MSRP)	$999

How It Stacks Up in the High-End Graphics Card Class

Its shader units figure is 26% above what is average for its class. Against the class average, the RTX 4080 Super is 15% higher on fp32 compute. The RTX 4080 Super is right in line with its class when it comes to vram.

Shader units

10,240 · class avg 8,119

FP32 compute

52.2 TFLOPS · class avg 45.4 TFLOPS

VRAM

16 GB · class avg 16 GB

Total board power

320 W · class avg 324 W

Ray tracing units

80 · class avg 81

Memory bandwidth

736 GB/s · class avg 814 GB/s