Processor and graphics card specifications are live

Graphics cards/Comparison

13 specifications

NVIDIA GeForce GTX 1070 vs AMD Radeon RX 5700

On paper, the AMD Radeon RX 5700 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.

NVIDIA GeForce GTX 1070 compared with AMD Radeon RX 5700, specification by specification
12 specifications · 2 with a higher side

NVIDIA GeForce GTX 1070

NVIDIA · GeForce GTX 10 · Desktop

AMD Radeon RX 5700

AMD · Radeon RX 5000 · Desktop

Compute

Architecture
Pascal
Not verified
Shading units
1,920
2,304 (higher on this specification)
Base clock
1506 MHz
Not verified
Boost clock
1683 MHz
1725 MHz (higher on this specification)
Game clock
Not verified
1625 MHz
Compute units
Not verified
36

Memory

Memory
8 GB
8 GB
Memory type
GDDR5
GDDR6
Memory bus
256-bit
256-bit

Power and platform

TDP
150 W
180 W
Process
Not verified
Not verified
Launched
2016-06-10
2019-07-07

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.

3 years apart

The RX 5700 (Radeon RX 5000, 2019) is 3 years newer than the GTX 1070 (Pascal, 2016). A newer architecture brings more than speed: newer video encoders and decoders, newer upscaling and frame generation, and a longer run of driver updates ahead of it.

Video memory

Both carry 8 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.

Memory bus

The GTX 1070 moves data over a 256-bit bus of GDDR5; the RX 5700 uses 256-bit GDDR6. The bus width and the memory type together set how fast the chip can reach its own memory, which shows at high resolutions where every frame moves more data. A narrow bus with fast memory can match a wide one with slow memory, so neither figure settles it alone.

Shading units

The counts differ, 2,304 against 1,920, but these are different designs from different makers, and a shading unit on one is not the same amount of work as on the other. The row cannot be used to rank this pair.

Board power

The RX 5700 draws up to 180 W against 150 W. That is heat the case has to exhaust and current the power supply has to deliver: allow a supply of about 600 W for the RX 5700 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
GTX 1070
150 W against 180 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.

Questions

Is the GTX 1070 better than the RX 5700?
By need, on the specifications: a small case or a modest power supply: the GTX 1070. They are different designs, so the raw counts cannot rank them. 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 RX 5700 need?
Allow about 600 W with a typical processor, and make sure the supply has the power connectors the card uses. The GTX 1070 at 150 W is easier on both.

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.