Nvidia GeForce RTX 4070 Super

Name: Nvidia GeForce RTX 4070 Super
Brand: Nvidia
SKU: 6393

Manufacturer: Nvidia

The Nvidia GeForce RTX 4070 Super is a graphics card based on the Ada Lovelace architecture, produced using a 5 nm fabrication process. It operates with a base clock of 1980 MHz and a turbo clock of 2480 MHz, and supports up to four simultaneous display outputs. The card does not include RGB lighting, keeping its aesthetic straightforward.

Memory configuration consists of 12GB of GDDR6X VRAM running at an effective speed of 21000 MHz over a 192-bit bus, providing a maximum bandwidth of 504.2 GB/s. With 7168 shading units, 224 texture mapping units, and 80 render output units, the card delivers 35.48 TFLOPS of floating-point performance and a texture rate of 554.4 GTexels/s. Feature support includes DirectX 12 Ultimate, OpenGL 4.6, OpenCL 3, ray tracing, DLSS, stereoscopic 3D, ECC memory, and Intel Resizable BAR. Connectivity is handled through one HDMI 2.1 port and three DisplayPort outputs, with no USB-C, DVI, or mini DisplayPort options. The card has a TDP of 220W, connects via PCIe 4, and measures 244 mm wide and 112 mm tall.

Pros

Ray tracing and DLSS are both supported, enabling advanced rendering and upscaling in compatible applications
ECC memory support provides data integrity assurance for workloads that require reliable memory accuracy
Double Precision Floating Point (DPFP) support makes the card usable for compute tasks that require 64-bit precision
Up to four displays can be connected simultaneously, offering flexibility for multi-monitor setups
Intel Resizable BAR is supported, allowing the CPU broader access to GPU memory during operation
At 244 mm wide and 112 mm tall, the card has a relatively compact physical footprint for its specification level

Cons

The 192-bit memory bus width places a ceiling on memory bandwidth that wider bus configurations would not have
No USB-C output is available, limiting compatibility with displays or devices that require it
DVI and mini DisplayPort outputs are absent, reducing options for users with older display hardware
Air-water cooling is not supported, so users who want liquid cooling integration must look elsewhere
RGB lighting is not included, which may matter to users who prioritize visual customization in their build

Who is this for?

The Nvidia GeForce RTX 4070 Super suits users who need a card capable of handling ray tracing and DLSS in graphically demanding applications, as both features are fully supported. Its ECC memory and Double Precision Floating Point support also make it a reasonable fit for users who run compute workloads alongside typical graphics tasks and require memory reliability. The compact physical dimensions of 244 mm by 112 mm make it a practical choice for builds where card length and height clearance are a concern, and the four-display output support accommodates users who work across multiple monitors.

Who is this NOT for?

Users who depend on USB-C, DVI, or mini DisplayPort connectivity will find the port selection restrictive, as none of these outputs are present. The card's 220W TDP makes it a poor fit for small form factor or thermally constrained builds where power delivery and airflow are limited. Those who want liquid or hybrid cooling integration will also need to look elsewhere, since air-water cooling is not supported, and users who prioritize RGB lighting in their system will find this card offers none.

Performance:

GPU clock speed	1980 MHz
GPU turbo	2480 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, reaching a turbo clock of 2480 MHz, with memory operating at 1313 MHz. The card's 7168 shading units work alongside 224 texture mapping units and 80 render output units to produce a texture rate of 554.4 GTexels/s and a pixel rate of 198 GPixel/s. Floating-point throughput stands at 35.48 TFLOPS, and Double Precision Floating Point (DPFP) is supported, extending the card's usefulness to workloads that require full 64-bit precision arithmetic.

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 features 12GB of GDDR6X VRAM running at an effective speed of 21000 MHz across a 192-bit memory bus, delivering a maximum bandwidth of 504.2 GB/s. ECC memory support is also included, which helps maintain data integrity for workloads where memory accuracy is critical.

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, covering the main graphics and compute APIs in common use. Ray tracing and DLSS are both enabled, while XeSS (XMX) is not supported. Multi-display technology is available with support for up to four connected displays, and stereoscopic 3D is also included. Intel Resizable BAR is supported, whereas LHR is not present. The card does not feature RGB lighting.

Ports:

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

Display connectivity is provided through one HDMI 2.1 port and three DisplayPort outputs, totaling four available display connections. There are no USB-C, DVI, or mini DisplayPort outputs on this card.

General info:

GPU architecture	Ada Lovelace
Thermal Design Power (TDP)	220W
PCI Express (PCIe) version	4
semiconductor size	5 nm
number of transistors	35800 million
Has air-water cooling	✕
width	244 mm
height	112 mm

The card is based on the Ada Lovelace architecture, built on a 5 nm process with a transistor count of 35,800 million. It interfaces with the system via PCIe 4 and carries a Thermal Design Power of 220W. Physically, it measures 244 mm in width and 112 mm in height, and it relies on air cooling only, as air-water cooling is not supported.

Final Verdict

The Nvidia GeForce RTX 4070 Super is a well-rounded graphics card that covers the core requirements of modern desktop use, with ray tracing, DLSS, ECC memory, and compute-capable DPFP support all present out of the box. Its 35.48 TFLOPS of floating-point throughput backed by 12GB of GDDR6X VRAM gives it a solid technical foundation, while its relatively compact dimensions make it easier to fit into a range of build configurations. The absence of USB-C output, liquid cooling support, and RGB lighting means it is a straightforward, no-frills card that prioritizes specification depth over visual customization or broad connectivity. For users whose needs align with what it offers, the RTX 4070 Super represents a capable and feature-complete option within the graphics card category.