Asus TUF Gaming GeForce RTX 4070 Super specifications and in-depth review

Asus TUF Gaming GeForce RTX 4070 Super

Manufacturer: Asus

The Asus TUF Gaming GeForce RTX 4070 Super is a graphics card built on Nvidia's Ada Lovelace architecture, fabricated on a 5 nm process with 35,800 million transistors. It runs at a base clock of 1980 MHz and boosts up to 2475 MHz, with a 225W TDP and physical dimensions of 301 mm × 139 mm. The card connects via PCIe 4 and relies on air cooling, with no air-water cooling option available.

Memory consists of 12GB of GDDR6X on a 192-bit bus running at an effective speed of 21,000 MHz, yielding a maximum bandwidth of 504.2 GB/s. The 7,168 shading units work with 224 texture mapping units and 80 render output units, producing 35.48 TFLOPS of floating-point throughput, a texture rate of 554.4 GTexels/s, and a pixel rate of 198 GPixel/s. The card supports DirectX 12 Ultimate, OpenGL 4.6, ray tracing, and DLSS, along with ECC memory and multi-display output across one HDMI 2.1a port and three DisplayPort connections for up to four simultaneous screens.

Pros
  • Ray tracing and DLSS support enable hardware-accelerated lighting and upscaling in compatible applications
  • 12GB of GDDR6X memory across a 192-bit bus at 21,000 MHz effective speed produces 504.2 GB/s of bandwidth
  • ECC memory support adds error-correction capability for compute-sensitive workloads
  • Up to four displays can be connected simultaneously via one HDMI 2.1a port and three DisplayPort outputs
  • DPFP support extends the card's utility to workloads requiring double precision numerical accuracy
  • RGB lighting is integrated into the card, providing visual customization out of the box
Cons
  • At 301 mm in length, the card demands a case with considerable internal clearance
  • No USB-C, DVI, or mini DisplayPort outputs are available, restricting display connectivity to standard HDMI and DisplayPort only
  • Air-water cooling is not supported, limiting thermal management to the included air-cooling solution
  • A single HDMI port may be restrictive for users relying on multiple HDMI-connected displays or devices
  • XeSS (XMX) is not supported, making the card incompatible with that specific upscaling technology
Who is this for?

This card is well-suited for users running ray tracing and DLSS-enabled workloads, where hardware acceleration for lighting and upscaling is a practical requirement. The combination of 35.48 TFLOPS, 504.2 GB/s of memory bandwidth, and ECC memory support also makes it a reasonable fit for compute-oriented tasks that benefit from both throughput and data integrity. Users operating multi-monitor setups of up to four displays will find the output configuration — one HDMI 2.1a and three DisplayPort connections — covers a broad range of display arrangements.

Who is this NOT for?

Users who need liquid or hybrid cooling will find this card limiting, as it relies solely on air cooling with no air-water option available. The 301 mm length also means it is not suited for compact or small-form-factor cases where physical clearance is restricted. Those who depend on USB-C display output or multiple HDMI connections will encounter constraints, as the card offers no USB-C ports and only a single HDMI output, and users whose workflows require XeSS (XMX) upscaling will find that feature absent.

Performance:

GPU clock speed 1980 MHz
GPU turbo 2475 MHz
pixel rate 198 GPixel/s
floating-point performance 35.48 TFLOPS
texture rate 554.4 GTexels/s
GPU memory speed 1313 MHz
shading units 7168
texture mapping units (TMUs) 224
render output units (ROPs) 80
Has Double Precision Floating Point (DPFP)

The GPU runs at a base clock of 1980 MHz and boosts up to 2475 MHz, driving a floating-point output of 35.48 TFLOPS. The 7,168 shading units are paired with 224 texture mapping units and 80 render output units, resulting in a texture rate of 554.4 GTexels/s and a pixel rate of 198 GPixel/s. GPU memory operates at 1313 MHz, and Double Precision Floating Point (DPFP) is supported, making the card capable of handling precision-sensitive compute tasks alongside standard graphics workloads.

Memory:

effective memory speed 21000 MHz
maximum memory bandwidth 504.2 GB/s
VRAM 12GB
GDDR version GDDR6X
memory bus width 192-bit
Supports ECC memory

The card is equipped with 12GB of GDDR6X VRAM running across a 192-bit memory bus at an effective speed of 21,000 MHz, delivering a maximum memory bandwidth of 504.2 GB/s. ECC memory support is also present, offering error-correction capability for workloads where data accuracy is a priority.

Features:

DirectX version DirectX 12 Ultimate
OpenGL version 4.6
OpenCL version 3
Supports multi-display technology
supports ray tracing
Supports 3D
supports DLSS
has XeSS (XMX)
AMD SAM / Intel Resizable BAR Intel Resizable BAR
has LHR
has RGB lighting
supported displays 4

The card supports DirectX 12 Ultimate, OpenGL 4.6, and OpenCL 3, providing broad API coverage for both graphics and compute use cases. Ray tracing and DLSS are both enabled, and stereoscopic 3D is also supported. Multi-display technology is available with a maximum of four simultaneous outputs, and Intel Resizable BAR is included. XeSS (XMX) and LHR are not supported, while RGB lighting is present on the card.

Ports:

has an HDMI output
HDMI ports 1
HDMI version HDMI 2.1a
DisplayPort outputs 3
USB-C ports 0
DVI outputs 0
mini DisplayPort outputs 0

Display connectivity is handled by one HDMI 2.1a port and three DisplayPort outputs, giving a total of four available connections. USB-C, DVI, and mini DisplayPort outputs are absent from this card's I/O configuration.

General info:

GPU architecture Ada Lovelace
Thermal Design Power (TDP) 225W
PCI Express (PCIe) version 4
semiconductor size 5 nm
number of transistors 35800 million
Has air-water cooling
width 301 mm
height 139 mm

The card is based on the Ada Lovelace architecture, built on a 5 nm process with 35,800 million transistors, and interfaces with the system over PCIe 4. It has a Thermal Design Power of 225W and uses air cooling only, as air-water cooling is not supported. Physically, it measures 301 mm in width and 139 mm in height.

Final Verdict

The Asus TUF Gaming GeForce RTX 4070 Super brings together a solid technical foundation — Ada Lovelace architecture, ray tracing, DLSS, and 504.2 GB/s of GDDR6X memory bandwidth — within a card that also covers multi-display output and ECC memory support for compute workloads. Its 301 mm length and reliance on air cooling alone are factors that narrow its fit to appropriately sized builds, and the absence of USB-C outputs and XeSS support will matter to a specific subset of users. Taken as a whole, the Asus TUF Gaming GeForce RTX 4070 Super is a technically capable graphics card that delivers a well-rounded feature set for users whose setups and workflows align with its configuration.

Popular Comparisons

Asus TUF Gaming GeForce RTX 4070 Super
Asus TUF Gaming GeForce RTX 4070 Super
VS
Asus ROG Strix GeForce RTX 4070 Ti Super
Asus ROG Strix GeForce RTX 4070 Ti Super