ASUS Prime -RTX5070-O12G-WHITE NVIDIA Geforce RTX 5070 12 GB GDDR7 90YV0M19-M0NA00

Primed for Power
Experience Primal performance with the Prime GeForce RTX 5070 White Edition, an SFF-Ready Enthusiast GeForce Card featuring a 2.5-slot design for expansive compatibility, enhanced by a triple-fan setup for supreme airflow design for supreme cooling.

NVIDIA Blackwell Architecture
The Ultimate Platform for Gamers and Creators

Fifth-Gen Tensor Cores
Max AI performance with FP4 and DLSS 4

New Streaming Multiprocessors
Optimized for neural shaders

Fourth-Gen Ray Tracing Cores
Built for Mega Geometry

Build Small. Play Big.
You can pack high performance into a smaller footprint with this SFF-Ready Enthusiast GeForce card. Look for cases that are compatible with SFF-Ready Enthusiast GeForce Cards to get a sure fit and streamline your PC build.

Cooling
2.5-slot Design
The Prime RTX 5070 White Edition features a 2.5 slot design with a carefully arranged layout for the shroud, heatsink and heat pipes to let the three Axial-tech fans leverage chassis side-panel ventilation and deliver optimal thermal performance.

Axial-tech Upgrades
Three tried-and-true Axial-tech fans feature a smaller hub that facilitates longer blades and a barrier ring to increase downward air pressure for lower temperatures, less noise and higher performance.

0dB Technology
All three fans come to a standstill when GPU temperatures are below 50?C, letting you play less demanding games or perform light tasks in relative silence. Fans start up again when temperatures are over 55?C, establishing a speed curve that balances performance and acoustics for work or play.

Dual Ball Fan Bearings
Different bearing types have unique pros and cons. Dual-ball bearings excel at durability and can last up to twice as long as sleeve bearing designs.

Vented Backplate
Large backplate vents significantly enhance heat dissipation, helping to keep the GPU cooler during intense tasks. This additional airflow helps ensure optimal temperatures, boosting performance, longevity and stability by defending against overheating and thermal throttling.

MaxContact Design
MaxContact is a special ASUS manufacturing process that effectively expands the surface area of the heat spreader that sits atop the GPU by 5%, compared to traditional designs. This improves temperatures by up to 2?C, in concert with an extensive heatsink array and powerful Axial-tech fans.

Phase-Change GPU Thermal Pad
By melting to effectively fill the gaps between the GPU and the thermal module, a premium phase-change GPU thermal pad provides superior thermal conductivity and enhanced heat dissipation, ensuring optimal performance and longevity for graphics cards under heavy loads.

Unmatched Reliability

ASUS GPU Guard & Bracket
ASUS GPU Guard applies adhesive to secure all four corners to reduce the risk of cracks, while a GPU bracket helps ensure uniform mounting pressure and extra stability.

Protective Backplate
The PCB is reinforced by a backplate that adds structural rigidity, helping to prevent flex and to protect components and trace pathways from damage.

Stainless Steel Bracket
The mounting bracket features grade 304 stainless steel, chosen for its strength and high resistance to corrosion.

Engineering

Dual BIOS
Do you prioritize low core temps or low noise levels? Performance mode lets the fans spin up to keep the card running cool all the time, and Quiet mode keeps the same power target and top-end settings while offering a less aggressive fan curve for quieter operation at moderate temperatures.

Auto?Extreme Technology
An automated manufacturing process that sets new standards in the industry by allowing all soldering to be completed in a single pass, ASUS Auto-Extreme technology reduces thermal strain on components and avoids the use of harsh cleaning chemicals, resulting in less environmental impact, lower manufacturing power consumption and a more reliable product overall.

Best PSU for the GeForce RTX 50 Series
Use the wattage calculator to estimate how much power you-ll need to fuel your rig, and then pick a compatible ROG, TUF Gaming or Prime power supply for ultimate performance.

Software

GPU Tweak III
The ASUS GPU Tweak III utility takes graphics card tuning to the next level. It lets you tweak critical parameters including GPU core clocks, memory frequency and voltage settings, with the option to monitor everything in real-time through a customizable on-screen display. Advanced fan control is also included along with many more features to help you get the most out of your graphics card.

Grow Your Dreams with AI Magic
MuseTree is an AI-powered image-generation app designed to spark your creativity. Effortlessly create and manage images and visual ideas, unlocking endless new inspirations. With its intuitive visual interface, generating stunning images has never been easier!

One Month of Free Adobe Creative Cloud
Enjoy all things AI at Adobe. Get complimentary membership to Adobe Creative Cloud with the purchase of select ASUS products, granting you access to all Adobe apps and Substance 3D.

RTX. It-s On.
The Ultimate in Ray Tracing and AI
RTX is the most advanced platform for full ray tracing and neural rendering technologies that are revolutionizing the ways we play and create. Over 700 games and applications use RTX to deliver realistic graphics and incredibly fast performance with cutting-edge AI features like DLSS Multi Frame Generation.

Creators
Your Creative AI-dvantage
NVIDIA Studio is your creative advantage. GeForce RTX 50 Series GPUs unlock transformative performance in video editing, 3D rendering, and graphic design. Experience RTX accelerations in top creative apps, world-class NVIDIA Studio drivers engineered and continually updated to provide maximum stability, and a suite of exclusive tools that harness the power of RTX for AI-assisted creative workflows.

Specs




Processor


CUDA

CUDA (aka Compute Unified Device Architecture) is a parallel computing platform and programming model created by NVIDIA and implemented by the graphics processing units (GPUs) that they produce. CUDA gives program developers direct access to the virtual instruction set and memory of the parallel computational elements in CUDA GPUs.




CUDA cores

6144


Graphics processor family

The category to which the graphics processor (GPU) belongs e.g. Southern Islands family of Radeon processors (made by AMD), GeForce 600 (made by NVIDIA).

NVIDIA


Graphics processor

Also known as a graphics processing unit (GPU), this is a specialized electronic circuit designed to rapidly manipulate and alter memory to accelerate the creation of images in a frame buffer intended for output to a display. GPUs are used in embedded systems, mobile phones, personal computers, workstations, and game consoles. Modern GPUs are very efficient at manipulating computer graphics.

GeForce RTX 5070


Processor boost clock speed

2557 MHz


Processor frequency (OC mode)

2587 MHz


Maximum resolution

The maximum number of pixels that can be displayed in the image. It is usually quoted as width - height,: for example, "1024 - 768" means the width is 1024 pixels and the height is 768 pixels.

7680 x 4320 pixels


Parallel processing technology support

Parallel processing technology is the simultaneous use of more than one CPU or processor core to execute a program or multiple computational threads. Ideally, parallel processing makes programs run faster because there are more engines (CPUs or Cores) running it. In practice, it is often difficult to divide a program in such a way that separate CPUs or cores can execute different portions without interfering with each other. Most computers have just one CPU, but some models have several, and multi-core processor chips are becoming the norm. There are even computers with thousands of CPUs.

Not supported


Maximum displays per videocard

4


Memory


Discrete graphics card memory
GB


Graphics card memory type

The type of memory used by the video card. Often a combination of dedicated memory (Video RAM or VRAM) and dynamic system memory is used. UMA stands for Unified Memory Architecture, and is a computer memory architecture that allows the graphics processing unit to share system memory. Other abreviations: RAM = Random Access Memory, SDRAM = synchronous dynamic RAM, DDR = double-data-rate.

GDDR7


Memory bus

Hardware and software that connects the main memory to the memory controller in computer systems. Originally, general-purpose buses like VMEbus and the S-100 bus were used, but to reduce latency, modern memory buses are designed to connect directly to DRAM chips, and thus are designed by chip standards bodies such as JEDEC.
2 bit


Data transfer rate

Rate at which data can be transferred. Usually expressed in units per second. May vary with network configurations.

28 Gbit/s


Ports & interfaces


Interface type

PCI Express 5.0


HDMI ports quantity

The number of sockets (ports) for HDMI connections. HDMI (High-Definition Multimedia Interface) is a compact audio/video interface for transferring uncompressed video data and compressed/uncompressed digital audio data from a HDMI-compliant device ("the source device") to a compatible computer monitor, video projector, digital television, or digital audio device. HDMI is a digital replacement for existing analog video standards.

1


HDMI version

2.1b


DisplayPorts quantity

Number of DisplayPorts. A DisplayPort is a digital display interface developed by the Video Electronics Standards Association (VESA). The interface is primarily used to connect a video source to a display device such as a computer monitor, though it can also be used to carry audio, USB, and other forms of data.

3


DisplayPort version

2.1b


Performance


OpenGL version

OpenGL (Open Graphics Library) is a specification defining a cross-language cross-platform API for writing applications that produce 3D computer graphics (and 2D computer graphics as well). The interface consists of over 250 different function calls which can be used to draw complex three-dimensional scenes from simple primitives.

4.6


Virtual Reality (VR) ready




HDCP

High-bandwidth Digital Content Protection (HDCP) is a form of digital copy protection to prevent copying of digital audio and video content as it travels across connections.




HDCP version

2.3


Dual Link DVI

A dual-link DVI interface sends data over both of the DVI links to the monitor, and this is how higher resolutions are achieved. With dual-link DVI, a resolution of 2048 x 1536 is possible.





Performance


NVIDIA G-SYNC




NPU performance up to

988 TOPs


Design


Cooling type

The method used to cool the device or to cool the air around the device.

Active


Cooling technology

ASUS Axial-tech


Number of fans

The quantity of fans (apparatus with rotating blades that creates a current of air for cooling or ventilation).

3 fan(s)


Form factor

The shape or design of the product.

Full-Height/Full-Length (FH/FL)


Number of slots

2.5


SFF ready




Product colour

The colour e.g. red, blue, green, black, white.

White


Power


Minimum system power supply

The lowest power that is needed.

750 W


Supplementary power connectors

1x 16-pin


System requirements


Windows operating systems supported

Windows vesions wich can be used with the device.




Weight & dimensions


Weight

Weight of the product without packaging (net weight). If possible, the net weight is given including standard accessories and supplies. Please note that sometimes the manufacturer leaves out the weight of accessories and/or supplies.

1.02 kg


Length

The measurement or extent of something from end to end.

304 mm


Depth

The distance from the front to the back of something.

50 mm


Height

The measurement of the product from head to foot or from base to top.
6 mm


Packaging data


Package width

The distance from one side of the packaging to the other.

405 mm


Package depth

The distance from the front to the back of the packaging.

233 mm


Package height

The distance from the top to the bottom of the packaging.

88.5 mm


Package weight

Weight of the packaged product.

1.67 kg


Package type

The type of product package e.g. box.

Box