TurboVS
Colorful GeForce RTX 4070 Super NB EX specifications and in-depth review

Colorful GeForce RTX 4070 Super NB EX

Manufacturer: Colorful

The Colorful GeForce RTX 4070 Super NB EX is a graphics card based on NVIDIA's Ada Lovelace architecture, manufactured on a 5 nm process with 35,800 million transistors. It operates at a base clock of 1980 MHz and boosts up to 2475 MHz, delivering 35.48 TFLOPS of floating-point performance. The card measures 325 mm in length and 134 mm in height, and draws 220W under load as defined by its thermal design power rating.

On the memory side, the card is equipped with 12GB of GDDR6X running across a 192-bit bus at an effective speed of 21000 MHz, providing up to 504 GB/s of bandwidth. It features 7168 shading units, 224 texture mapping units, and 80 render output units, with a texture rate of 554.4 GTexels/s and a pixel rate of 198 GPixel/s. Display output is handled through one HDMI 2.1 port and three DisplayPort connectors, supporting up to four monitors simultaneously. The card supports DirectX 12 Ultimate, OpenGL 4.6, ray tracing, and DLSS, and connects via a PCIe 4.0 interface with Intel Resizable BAR compatibility.

Pros
  • Boosts up to 2475 MHz with 35.48 TFLOPS of floating-point performance, making it capable of handling demanding rendering and compute workloads
  • 12GB of GDDR6X memory running at 21000 MHz effective speed delivers 504 GB/s of bandwidth, supporting high-resolution textures and large scene data
  • Supports ray tracing and DLSS, enabling more realistic lighting in compatible titles alongside AI-driven resolution scaling
  • ECC memory support adds a layer of data integrity useful for compute-intensive or professional tasks
  • Three DisplayPort outputs and one HDMI 2.1 port allow connection of up to four displays simultaneously
  • Intel Resizable BAR support enables the CPU to access the full GPU frame buffer, which can improve data transfer efficiency
Cons
  • 220W TDP requires adequate system power delivery and case airflow planning
  • No USB-C output limits compatibility with certain modern monitors and displays that rely on that connection
  • Does not include liquid cooling support, so thermal management depends entirely on the air cooler configuration
  • No RGB lighting for users who prioritize visual customization within their build
  • 192-bit memory bus width is narrower than higher-tier cards in the same generation, which may limit memory throughput in the most bandwidth-intensive scenarios
Who is this for?

This card is well-matched for users running ray tracing and DLSS-enabled titles at high resolutions, where its 35.48 TFLOPS of compute throughput and 504 GB/s of memory bandwidth can be fully utilized. It also suits those working with multi-monitor setups, as its four-display output capacity across HDMI 2.1 and three DisplayPort connections covers a wide range of desktop configurations. The inclusion of ECC memory support and Double Precision Floating Point capability makes it a reasonable fit for users who occasionally run compute or data-integrity-sensitive workloads alongside their primary graphics use.

Who is this NOT for?

Users who require USB-C display connectivity will find this card limiting, as it offers no such output. Those building compact or thermally constrained systems may also face challenges, given the card's 220W TDP and the absence of liquid cooling support — it depends entirely on case airflow and the bundled air cooler. Additionally, users pushing the most bandwidth-intensive workloads where a wider memory bus is critical may find the 192-bit interface a bottleneck compared to what higher-tier configurations in the same generation can offer.

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 Colorful GeForce RTX 4070 Super NB EX runs at a base clock of 1980 MHz, boosting up to 2475 MHz under load, and delivers 35.48 TFLOPS of floating-point performance alongside a texture rate of 554.4 GTexels/s and a pixel rate of 198 GPixel/s. It is equipped with 7168 shading units, 224 texture mapping units (TMUs), and 80 render output units (ROPs), with GPU memory operating at 1313 MHz. The card also supports Double Precision Floating Point (DPFP), broadening its suitability for compute-oriented workloads beyond standard rendering tasks.

Memory:

effective memory speed 21000 MHz
maximum memory bandwidth 504 GB/s
VRAM 12GB
GDDR version GDDR6X
memory bus width 192-bit
Supports ECC memory ✓

The card features 12GB of GDDR6X video memory operating at an effective speed of 21000 MHz across a 192-bit bus, yielding a maximum memory bandwidth of 504 GB/s. ECC memory support is also included, which helps detect and correct memory errors — a useful capability for workloads that require data integrity.

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

This card supports DirectX 12 Ultimate, OpenGL 4.6, and OpenCL 3, covering a broad range of graphics and compute workloads. Ray tracing and DLSS are both supported, along with stereoscopic 3D and multi-display technology spanning up to four screens simultaneously. Intel Resizable BAR is available for improved CPU-to-GPU data throughput, while XeSS (XMX) and LHR are not present on this model. The card does not include 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

The card's output configuration consists of one HDMI 2.1 port and three DisplayPort outputs, with no USB-C, DVI, or mini DisplayPort connections present. This straightforward layout keeps the focus on the two most widely used modern display interfaces, making it well-suited for multi-monitor setups within those standards.

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 325 mm
height 134 mm

Built on the Ada Lovelace architecture, this card uses a 5 nm manufacturing process and integrates 35,800 million transistors, connecting to the system via a PCIe 4.0 interface. It carries a Thermal Design Power rating of 220W and relies solely on air cooling, with no liquid cooling support included. Physically, the card measures 325 mm in width and 134 mm in height.

Final Verdict

The Colorful GeForce RTX 4070 Super NB EX brings together a capable set of specifications under Ada Lovelace — most notably its 35.48 TFLOPS of floating-point performance paired with 504 GB/s of memory bandwidth — making it a solid choice for users who want ray tracing, DLSS support, and multi-display flexibility in a single card. Its 220W power draw and reliance on air cooling mean it fits best in well-ventilated builds, and the absence of USB-C output is worth noting for those with specific display requirements. Overall, it represents a well-rounded option for users whose needs align with what its port selection, feature set, and thermal profile can realistically deliver.