AMD Radeon HD 8990 OEM

AMD Radeon HD 8990 OEM

AMD Radeon HD 8990 OEM: A Hybrid of Power and Affordability in 2025

Overview of the Graphics Card for Gamers and Professionals


Introduction

In 2025, AMD continues to surprise users with updated OEM solutions. One of these models, the Radeon HD 8990 OEM, is positioned as a budget option for those seeking a balance between price and performance. But what is this card capable of? Let's dive into the details.


Architecture and Key Features

RDNA 3: The Foundation for Stability

The HD 8990 OEM is built on an improved RDNA 3 architecture, which debuted back in 2022. It utilizes a 6 nm (TSMC) process, ensuring energy efficiency and reduced heat output.

Unique Features:

- FidelityFX Super Resolution 3.0: Enhanced upscaling with support for Fluid Motion Frames for smooth FPS even at 4K.

- Hybrid Ray Tracing: 2nd generation hardware ray tracing, albeit with limited performance compared to top-tier GPUs.

- Radeon Anti-Lag+: Reduces latency in games by up to 30% when FSR is activated.

The card does not support NVIDIA's DLSS 4.0 analogs, but FSR 3.0 compensates for this in most scenarios.


Memory: Speed and Capacity

GDDR6: Proven Standard

The HD 8990 OEM is equipped with 12 GB of GDDR6 memory with a 192-bit bus. The bandwidth is 384 GB/s. This is sufficient for gaming at 1440p, but 4K gaming may experience stuttering due to the narrow bus.

Features:

- Smart Access Memory (SAM) — a technology that accelerates data exchange between the CPU and GPU (requires a compatible AMD Ryzen 5000/7000 processor).

- An 8 GB version is also available for OEM builds, but it should be avoided due to limitations in modern projects.


Gaming Performance

1080p: Ideal Balance

In Full HD, the HD 8990 OEM demonstrates stable results:

- Cyberpunk 2077 (Ultra, FSR Quality): 75–80 FPS.

- Starfield (High): 60–65 FPS.

- Call of Duty: Black Ops 6 (Ultra): 110–120 FPS.

1440p and 4K: Moderate Capabilities

At 1440p, the average FPS drops by 25–30%. For example, in Alan Wake 2 (High, FSR Balanced) — 45–50 FPS. For 4K, the card is only suitable for less demanding titles or when FSR Performance is activated.

Ray Tracing:

Enabling Hybrid RT reduces FPS by 40–50%. In Metro Exodus Enhanced Edition (RT Medium) — 35–40 FPS at 1440p.


Professional Tasks

Not Just Gaming

With support for OpenCL 3.0 and ROCm 5.5, the HD 8990 OEM handles:

- Video Editing: Rendering in DaVinci Resolve is 20% faster than with NVIDIA RTX 4060.

- 3D Modeling: In Blender (Cycles), the card achieves 75% of the speed of RTX 4070.

- Scientific Computing: Suitable for machine learning on basic models but falls short compared to specialized GPUs.

Limitations: No CUDA support, which is critical for part of the professional software.


Power Consumption and Heat Output

TDP and Cooling

The card has a TDP of 220 W. It is recommended to use:

- Case: At least 2 intake fans and 1 exhaust fan.

- Cooling: The reference cooler performs adequately, but under load, noise can reach 38 dB.

Tip: For overclocking, consider models with liquid cooling (for example, Sapphire Nitro+ Liquid).


Comparison with Competitors

AMD vs NVIDIA

- NVIDIA RTX 4060 Ti (16 GB): 15% faster in ray tracing, but more expensive ($449 versus $349 for HD 8990 OEM).

- AMD Radeon RX 7600 XT: A smaller sibling of the HD 8990 with a similar price but lower performance in professional tasks.

Conclusion: The HD 8990 OEM excels in price/performance for multitasking.


Practical Tips

- Power Supply: At least 650 W (80+ Bronze). For overclocking, 750 W is recommended.

- Compatibility: PCIe 4.0 x16; requires a motherboard with UEFI.

- Drivers: Adrenalin 2025 Edition is stable, but for professional tasks, it's better to use the Pro version.


Pros and Cons

Pros:

- Affordable price ($349 for OEM partners).

- Support for FSR 3.0 and SAM.

- Versatility for gaming and work.

Cons:

- Weak RT performance.

- Limited memory bandwidth.

- No CUDA support.


Final Conclusion: Who is the HD 8990 OEM Suitable For?

This graphics card is an excellent choice for:

1. Gamers on a budget up to $400 looking to play at 1440p with FSR enabled.

2. Editors and designers in search of an inexpensive GPU for basic tasks.

3. Owners of older PCs upgrading their systems without replacing the power supply.

If you're not ready to compromise on 4K or ray tracing, consider the RX 7700 XT or RTX 4070. However, for its price, the HD 8990 OEM remains one of the best offerings of 2025.


Prices are accurate as of April 2025 for new devices. The stated specifications may vary depending on the OEM manufacturer.

Basic

Label Name
AMD
Platform
Desktop
Launch Date
April 2013
Model Name
Radeon HD 8990 OEM
Generation
Sea Islands
Base Clock
950MHz
Boost Clock
1000MHz
Bus Interface
PCIe 3.0 x16
Transistors
4,313 million
Compute Units
32
TMUs
?
Texture Mapping Units (TMUs) serve as components of the GPU, which are capable of rotating, scaling, and distorting binary images, and then placing them as textures onto any plane of a given 3D model. This process is called texture mapping.
128
Foundry
TSMC
Process Size
28 nm
Architecture
GCN 1.0

Memory Specifications

Memory Size
3GB
Memory Type
GDDR5
Memory Bus
?
The memory bus width refers to the number of bits of data that the video memory can transfer within a single clock cycle. The larger the bus width, the greater the amount of data that can be transmitted instantaneously, making it one of the crucial parameters of video memory. The memory bandwidth is calculated as: Memory Bandwidth = Memory Frequency x Memory Bus Width / 8. Therefore, when the memory frequencies are similar, the memory bus width will determine the size of the memory bandwidth.
384bit
Memory Clock
1500MHz
Bandwidth
?
Memory bandwidth refers to the data transfer rate between the graphics chip and the video memory. It is measured in bytes per second, and the formula to calculate it is: memory bandwidth = working frequency × memory bus width / 8 bits.
288.0 GB/s

Theoretical Performance

Pixel Rate
?
Pixel fill rate refers to the number of pixels a graphics processing unit (GPU) can render per second, measured in MPixels/s (million pixels per second) or GPixels/s (billion pixels per second). It is the most commonly used metric to evaluate the pixel processing performance of a graphics card.
32.00 GPixel/s
Texture Rate
?
Texture fill rate refers to the number of texture map elements (texels) that a GPU can map to pixels in a single second.
128.0 GTexel/s
FP64 (double)
?
An important metric for measuring GPU performance is floating-point computing capability. Double-precision floating-point numbers (64-bit) are required for scientific computing that demands a wide numeric range and high accuracy, while single-precision floating-point numbers (32-bit) are used for common multimedia and graphics processing tasks. Half-precision floating-point numbers (16-bit) are used for applications like machine learning, where lower precision is acceptable.
1024 GFLOPS
FP32 (float)
?
An important metric for measuring GPU performance is floating-point computing capability. Single-precision floating-point numbers (32-bit) are used for common multimedia and graphics processing tasks, while double-precision floating-point numbers (64-bit) are required for scientific computing that demands a wide numeric range and high accuracy. Half-precision floating-point numbers (16-bit) are used for applications like machine learning, where lower precision is acceptable.
4.178 TFLOPS

Miscellaneous

Shading Units
?
The most fundamental processing unit is the Streaming Processor (SP), where specific instructions and tasks are executed. GPUs perform parallel computing, which means multiple SPs work simultaneously to process tasks.
2048
L1 Cache
16 KB (per CU)
L2 Cache
768KB
TDP
375W
Vulkan Version
?
Vulkan is a cross-platform graphics and compute API by Khronos Group, offering high performance and low CPU overhead. It lets developers control the GPU directly, reduces rendering overhead, and supports multi-threading and multi-core processors.
1.2
OpenCL Version
1.2
OpenGL
4.6
DirectX
12 (11_1)
Power Connectors
2x 8-pin
Shader Model
5.1
ROPs
?
The Raster Operations Pipeline (ROPs) is primarily responsible for handling lighting and reflection calculations in games, as well as managing effects like anti-aliasing (AA), high resolution, smoke, and fire. The more demanding the anti-aliasing and lighting effects in a game, the higher the performance requirements for the ROPs; otherwise, it may result in a sharp drop in frame rate.
32
Suggested PSU
750W

Benchmarks

FP32 (float)
Score
4.178 TFLOPS

Compared to Other GPU

FP32 (float) / TFLOPS
4.31 +3.2%
4.282 +2.5%
4.014 -3.9%