TurboVS
AX Gaming GeForce RTX 5090 D X3W specifications and in-depth review

AX Gaming GeForce RTX 5090 D X3W

Manufacturer: AX Gaming

The AX Gaming GeForce RTX 5090 D X3W is a high-end graphics card based on NVIDIA's Blackwell architecture, manufactured on a 5 nm process with 92,200 million transistors. It carries a base GPU clock of 2017 MHz with a boost ceiling of 2407 MHz, and its 32GB GDDR7 frame buffer runs across a wide 512-bit memory bus, delivering up to 1790 GB/s of memory bandwidth. The card supports ray tracing, DLSS, and DirectX 12 Ultimate, and comes equipped with RGB lighting for those who factor aesthetics into their build decisions.

On the output side, the AX Gaming RTX 5090 D X3W provides three DisplayPort connectors alongside one HDMI 2.1b port, supporting up to four displays simultaneously. It draws up to 575W under load as rated by its TDP, connects via PCIe 5.0, and measures 358 mm in length by 148 mm in height. The card also includes support for Intel Resizable BAR and ECC memory, alongside OpenCL 3.0 and OpenGL 4.6 compatibility, rounding out a broad feature set suited to demanding workloads and content creation pipelines.

Pros
  • 32GB of GDDR7 VRAM across a 512-bit bus provides substantial headroom for memory-intensive workloads
  • ECC memory support adds a layer of data integrity for tasks where accuracy matters
  • Supports up to four simultaneous displays, making it practical for multi-monitor setups
  • Ray tracing and DLSS are both supported, expanding compatibility with modern rendering pipelines
  • Intel Resizable BAR support allows the CPU to access the full GPU frame buffer, which can improve data transfer efficiency
  • The card includes RGB lighting, giving users control over the visual appearance of their build
Cons
  • A TDP of 575W places significant demands on the power supply and system cooling infrastructure
  • Air-water cooling is not included, so thermal management relies entirely on the card's own air cooling solution
  • There are no USB-C outputs, which limits connectivity options for certain modern displays and devices
  • The 358 mm length may pose fitment challenges in smaller or mid-tower cases
  • XeSS (XMX) is not supported, narrowing upscaling options to DLSS only
Who is this for?

This card is well suited to users running memory-intensive and compute-heavy workloads, given its 32GB of GDDR7 VRAM, ECC memory support, and Double Precision Floating Point capability — making it a practical fit for 3D rendering, simulation, and professional content creation pipelines. The combination of ray tracing, DLSS, and DirectX 12 Ultimate support also makes it appropriate for users engaged in high-fidelity real-time rendering and modern game development workflows. Those building multi-monitor workstations will find the four-display support and three DisplayPort outputs useful for expansive desktop configurations.

Who is this NOT for?

The card's 575W TDP makes it poorly suited to users with limited power delivery capacity or smaller form-factor systems, as it demands a robust power supply and adequate airflow that compact builds typically cannot accommodate. Users working in space-constrained cases may also struggle with the 358 mm card length, which exceeds what many mid-tower enclosures can comfortably house. Additionally, those who rely on USB-C display connectivity or require XeSS-based upscaling will find this card lacking the necessary output options and upscaling compatibility to support those workflows.

Performance:

GPU clock speed 2017 MHz
GPU turbo 2407 MHz
pixel rate 423.6 GPixel/s
floating-point performance 104.8 TFLOPS
texture rate 1637 GTexels/s
GPU memory speed 1750 MHz
shading units 21760
texture mapping units (TMUs) 680
render output units (ROPs) 176
Has Double Precision Floating Point (DPFP) ✓

The Performance section of this card centers on a base GPU clock of 2017 MHz that scales up to 2407 MHz in turbo mode, backed by 21,760 shading units, 680 texture mapping units, and 176 render output units. These figures translate into a texture rate of 1637 GTexels/s and a pixel rate of 423.6 GPixel/s, with 104.8 TFLOPS of floating-point performance available for compute-intensive tasks. GPU memory operates at 1750 MHz, and the card includes support for Double Precision Floating Point, making it capable of handling workloads that require high numerical accuracy.

Memory:

effective memory speed 28000 MHz
maximum memory bandwidth 1790 GB/s
VRAM 32GB
GDDR version GDDR7
memory bus width 512-bit
Supports ECC memory ✓

This card is equipped with 32GB of GDDR7 VRAM running across a 512-bit memory bus, with an effective memory speed of 28,000 MHz that yields a maximum bandwidth of 1790 GB/s. ECC memory support is also present, allowing the card to detect and correct memory errors, which is particularly relevant for workloads where data integrity 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, covering a broad range of graphics and compute APIs. Ray tracing and DLSS are both supported, alongside stereoscopic 3D and multi-display technology that allows up to four screens to be connected simultaneously. Intel Resizable BAR is available for improved CPU-to-GPU data access, and RGB lighting is built in. XeSS (XMX) and LHR are not present on this card.

Ports:

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

The card's output configuration consists of three DisplayPort connectors and one HDMI 2.1b port, providing four video outputs in total. There are no USB-C, DVI, or mini DisplayPort outputs on this model.

General info:

GPU architecture Blackwell
Thermal Design Power (TDP) 575W
PCI Express (PCIe) version 5
semiconductor size 5 nm
number of transistors 92200 million
Has air-water cooling ✕
width 358 mm
height 148 mm

Built on the Blackwell architecture and fabricated at 5 nm, this card integrates 92,200 million transistors and connects to the system via PCIe 5.0. It carries a TDP of 575W and does not include air-water cooling. Physically, the card measures 358 mm in width and 148 mm in height.

Final Verdict

The AX Gaming GeForce RTX 5090 D X3W is a specification-dense graphics card built around NVIDIA's Blackwell architecture, and its 32GB of GDDR7 VRAM paired with 1790 GB/s of memory bandwidth positions it firmly at the demanding end of the workload spectrum. It covers the full range of modern rendering and compute requirements — ray tracing, DLSS, DirectX 12 Ultimate, ECC memory, and Double Precision Floating Point support all come as standard — making it a capable choice for users whose workloads genuinely require this level of resource. That said, the 575W TDP and 358 mm physical footprint mean that realizing its full potential requires a system specifically built to accommodate it. For users with the infrastructure to support it, the RTX 5090 D X3W delivers a thorough and well-rounded feature set for both professional and advanced creative use cases.

Popular Comparisons

AX Gaming GeForce RTX 5090 D X3W
AX Gaming GeForce RTX 5090 D X3W
VS
Colorful iGame GeForce RTX 5070 Ti Ultra W OC
Colorful iGame GeForce RTX 5070 Ti Ultra W OC