TurboVS
Manli Stellar GeForce RTX 5090 OC specifications and in-depth review

Manli Stellar GeForce RTX 5090 OC

Manufacturer: Manli

The Manli Stellar GeForce RTX 5090 OC is a high-end graphics card based on NVIDIA's Blackwell architecture, manufactured on a 5 nm process with 92,200 million transistors. Running at a base clock of 2017 MHz with a boost reaching 2437 MHz, it delivers 106.1 TFLOPS of floating-point performance and is equipped with 21,760 shading units alongside 680 texture mapping units and 176 render output units. The card carries a TDP of 575W and measures 360 mm in length and 146 mm in height, with RGB lighting included.

On the memory side, the card features 32GB of GDDR7 VRAM on a 512-bit bus running at an effective speed of 28,000 MHz, yielding a maximum bandwidth of 1,792 GB/s. It supports ECC memory and offers a pixel rate of 428.9 GPixel/s alongside a texture rate of 1,657 GTexels/s. Connectivity includes one HDMI 2.1b port and three DisplayPort outputs, supporting up to four displays simultaneously. Feature support spans DirectX 12 Ultimate, OpenGL 4.6, OpenCL 3, ray tracing, DLSS, stereoscopic 3D, and Intel Resizable BAR, while the card connects via PCIe 5.

Pros
  • The 32GB of GDDR7 VRAM across a 512-bit bus provides substantial memory capacity for memory-intensive workloads and high-resolution rendering
  • With 21,760 shading units, 680 texture mapping units, and 176 ROPs, the card is configured for handling complex scenes with high geometry and texture density
  • Support for ray tracing and DLSS together offers flexibility for workloads that benefit from both real-time lighting accuracy and AI-based upscaling
  • ECC memory support adds a layer of data integrity protection useful in compute and professional workflows
  • Driving up to four displays simultaneously via one HDMI 2.1b port and three DisplayPort outputs makes it well-suited for multi-monitor setups
  • Intel Resizable BAR support allows the CPU broader access to GPU memory, which can improve data transfer efficiency
Cons
  • A TDP of 575W places significant demands on power supply capacity and system cooling infrastructure
  • The card measures 360 mm in length and 146 mm in height, requiring a large case with adequate clearance for installation
  • Multi-GPU configurations are not supported, limiting scalability for users who rely on linked GPU setups
  • There are no USB-C, DVI, or mini DisplayPort outputs, which restricts compatibility with certain older or specialized display hardware
  • Air-water hybrid cooling is not included, so thermal management depends entirely on the card's air cooling solution
Who is this for?

This card is well-suited to users who work with high-resolution rendering and compute-intensive tasks, given its 106.1 TFLOPS of floating-point performance, double precision floating point support, and ECC memory — all of which are relevant to 3D rendering, simulation, and professional GPU compute workflows. The 32GB of GDDR7 VRAM with 1,792 GB/s of bandwidth makes it particularly appropriate for workloads that involve large datasets or complex scene geometry. Users building multi-monitor workstations will also find the four-display output support practical, and those who take advantage of ray tracing pipelines or DLSS-enabled applications will benefit from native support for both features.

Who is this NOT for?

The card's 575W TDP and 360 mm length make it a poor fit for compact or small-form-factor builds, as it demands a spacious case, robust power delivery, and strong system airflow that many mid-range or space-constrained setups cannot accommodate. Users who rely on multi-GPU configurations will find no support for that here, making it unsuitable for scaled rendering farms or legacy SLI-style workflows. Additionally, those who require USB-C video output or need to connect DVI-based displays will face compatibility issues, as neither port type is present on this card.

Performance:

GPU clock speed 2017 MHz
GPU turbo 2437 MHz
pixel rate 428.9 GPixel/s
floating-point performance 106.1 TFLOPS
texture rate 1657 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 Manli Stellar GeForce RTX 5090 OC operates at a base GPU clock of 2017 MHz, boosting up to 2437 MHz under load, while the GPU memory runs at 1750 MHz. With 106.1 TFLOPS of floating-point performance and support for double precision floating point, the card handles compute-intensive workloads alongside demanding graphics tasks. It is equipped with 21,760 shading units, 680 texture mapping units, and 176 render output units, translating into a texture rate of 1657 GTexels/s and a pixel rate of 428.9 GPixel/s.

Memory:

effective memory speed 28000 MHz
maximum memory bandwidth 1792 GB/s
VRAM 32GB
GDDR version GDDR7
memory bus width 512-bit
Supports ECC memory ✓

The card is equipped with 32GB of GDDR7 VRAM running across a 512-bit memory bus, reaching an effective memory speed of 28,000 MHz and delivering a maximum memory bandwidth of 1,792 GB/s. ECC memory support is included, which helps maintain data integrity during sustained workloads.

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
multi-GPU 0
has RGB lighting ✓
supported displays 4

The Manli Stellar GeForce RTX 5090 OC 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, while XeSS (XMX) is not available on this card. It can drive up to four displays simultaneously through its multi-display support, and Intel Resizable BAR is included to help improve data transfer between the CPU and GPU. Multi-GPU configurations are not supported, and the card features RGB lighting. Stereoscopic 3D is also supported for compatible setups.

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 one HDMI 2.1b port and three DisplayPort outputs, providing a total of four video connections for multi-monitor setups. There are no USB-C, DVI, or mini DisplayPort outputs available 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 360 mm
height 146 mm

The Manli Stellar GeForce RTX 5090 OC is built on the Blackwell architecture, using a 5 nm manufacturing process and integrating 92,200 million transistors. It connects via PCIe 5 and carries a Thermal Design Power of 575W, reflecting the demands of its hardware configuration. The card measures 360 mm in width and 146 mm in height, and does not include air-water cooling. Physical dimensions aside, it relies solely on its own cooling solution without hybrid liquid cooling support.

Final Verdict

The Manli Stellar GeForce RTX 5090 OC is a specification-dense graphics card built around the Blackwell architecture, combining substantial compute throughput with 32GB of high-bandwidth GDDR7 VRAM in a configuration aimed squarely at demanding rendering, compute, and multi-display workloads. Its support for ray tracing, DLSS, ECC memory, and Intel Resizable BAR rounds out a feature set that addresses both graphics-heavy and professional GPU compute scenarios. That said, its 575W power draw and 360 mm physical footprint impose real system requirements that limit its compatibility to well-resourced builds. For users whose environments can meet those demands, the Manli Stellar GeForce RTX 5090 OC represents a thoroughly capable option for high-complexity workloads — though those working in constrained or compact setups should factor in those hardware requirements carefully before committing.

Popular Comparisons

Manli Stellar GeForce RTX 5090 OC
Manli Stellar GeForce RTX 5090 OC
VS
Gigabyte GeForce RTX 5090 WindForce
Gigabyte GeForce RTX 5090 WindForce