13 specifications

NVIDIA GeForce RTX 4070 Ti SUPER vs NVIDIA GeForce RTX 4080 SUPER

On paper, the NVIDIA GeForce RTX 4080 SUPER has more shading units. Specifications describe what each card is designed to do; how much of that either one holds under continuous load is a separate question.

10 specifications · 3 with a higher side

Full specifications

NVIDIA GeForce RTX 4070 Ti SUPER

NVIDIA · GeForce RTX 40 · Desktop

Full specifications

NVIDIA GeForce RTX 4080 SUPER

NVIDIA · GeForce RTX 40 · Desktop

Compute

Architecture

Ada Lovelace

Shading units

8,448

10,240

Base clock

2340 MHz

2290 MHz

Boost clock

2610 MHz

2550 MHz

Memory

16 GB

Memory type

GDDR6X

Memory bus

256-bit

Power and platform

TDP

285 W

320 W

Process

Not verified

Launched

2024-01-24

2024-01-31

A check marks the higher figure only on rows where higher is unambiguously better. Rows without one are not ties; they are specifications where “better” has no meaning.

Reading the table

What the difference means.

The same architecture

Both are Ada Lovelace cards from NVIDIA, so their figures can be read against each other directly, and the features are the same on both. The differences in the table are the whole difference.

Video memory

Both carry 16 GB, so neither has the advantage where memory is the limit: high resolutions, heavy textures and local AI models fill both at the same point.

Shading units

The RTX 4080 SUPER has 10,240 shading units against 8,448, 21 percent more of the same kind of core. Within one architecture that is the clearest single guide to how much more work the chip can do, provided it is given the power and cooling to use them.

Board power

The RTX 4080 SUPER draws up to 320 W against 285 W. That is heat the case has to exhaust and current the power supply has to deliver: allow a supply of about 750 W for the RTX 4080 SUPER with a typical processor, and check the card's power connectors against the supply's. A card that cannot shed its heat does not fail. It lowers its clocks after a few minutes, which is the frame rate that falls the longer you play.

Which to pick, on paper

A small case or a modest power supply: RTX 4070 Ti SUPER; 285 W against 320 W: less heat, fewer power connectors, quieter fans.

What no table says

How much of its speed a graphics card keeps after the first minute depends on the cooling and the power limit of the machine it is in. If you own one of these, measure it: the test is free and runs in this browser.

Free GPU stress test

Questions

Is the RTX 4070 Ti SUPER better than the RTX 4080 SUPER?: By need, on the specifications: a small case or a modest power supply: the RTX 4070 Ti SUPER. They share an architecture, so the table is a fair guide. Frame rates depend on the game and its settings, and how much speed either card keeps after ten minutes depends on its cooling, which is what a sustained test measures.
What power supply does the RTX 4080 SUPER need?: Allow about 750 W with a typical processor, and make sure the supply has the power connectors the card uses. The RTX 4070 Ti SUPER at 285 W is easier on both.
Do the RTX 4070 Ti SUPER and the RTX 4080 SUPER have the same features?: Yes. Both are Ada Lovelace designs from NVIDIA, so they share the same generation of video encoders and decoders, upscaling and driver support. What separates them is in the table: how much of the chip each one has, and how much power it is given.

More comparisons

Every figure on this table is a design target. None of it is a measurement.

Nothing above describes how a graphics card behaves twenty minutes into a sustained workload, which is where two chips with nearly identical specifications routinely diverge. A boost clock is a ceiling the vendor permits, not a rate the chip sustains, and whether it holds depends on the cooling, the case, the power profile and the room. None of those appear on a specification sheet.

We deliberately do not reduce these figures to a single score. A composite invented from specifications would look authoritative and measure nothing, and choosing the weights would be choosing the winner.

Run the test on your machine How we measure →