NVIDIA GeForce GTX 960 OEM

NVIDIA GeForce GTX 960 OEM

NVIDIA GeForce GTX 960 OEM in 2025: Is It Worth Buying an Outdated Graphics Card?

April 2025

In an era where graphics cards with support for ray tracing and neural technologies have become the norm, the NVIDIA GeForce GTX 960 OEM appears as a relic of the past. However, even in 2025, this model attracts the attention of budget users. Let’s examine who might find it useful and what compromises will have to be made.


1. Architecture and Key Features

Maxwell Architecture: A Modest Legacy

The GTX 960 OEM is based on the Maxwell architecture (GM206), released in 2015. It is a 28nm chip optimized for a balance between performance and energy efficiency. Compared to modern solutions built on 5nm and 6nm processes (such as the RTX 50 series), its manufacturing technology is outdated, but Maxwell was considered a breakthrough in its time.

Unique Features: What’s Missing

The card lacks support for ray tracing (RTX), DLSS, FidelityFX, or any other modern technologies. The "features" it offers are limited to basic functionalities like VXGI (global illumination in some games) and MFAA (anti-aliasing). For games in 2025, these capabilities are insufficient, but they may still be useful in older projects and indie titles.


2. Memory: Limitations That Impact Performance

Type and Size: GDDR5 and Modest 2/4 GB

The GTX 960 OEM comes with GDDR5 memory and a 128-bit bus. The size depends on the version: 2 GB (base) or 4 GB (OEM version). The bandwidth ranges from 112–144 GB/s, which is 3-4 times lower than modern GDDR6X solutions.

Impact on Performance

Even 4 GB of video memory is critically low in 2025. For instance, in games like Cyberpunk 2077: Phantom Liberty (minimum settings, 1080p), the card delivers around 20–25 FPS due to a lack of VRAM. In less demanding projects, such as Fortnite or CS2, the average FPS reaches 40–60 frames but with frequent drops.


3. Gaming Performance: Realities of 2025

1080p: The Ceiling for Comfortable Gaming

- Apex Legends (low settings): 50–60 FPS.

- The Witcher 3 (medium settings): 35–45 FPS.

- Hogwarts Legacy (minimum settings): 15–20 FPS.

1440p and 4K: Not Feasible for GTX 960 OEM

Even at 1440p resolution, most games become virtually unplayable. For example, Elden Ring at 1440p yields 10–15 FPS. 4K is out of the question — that's territory for RTX 4060 and above.

Ray Tracing: No Support

The card lacks hardware RT Cores, so ray tracing is off the table. Software emulation (e.g., via mods) reduces FPS to 1–5 frames, which is unacceptable.


4. Professional Tasks: Looking Back on the Past

Video Editing and 3D Modeling

Thanks to CUDA support (1024 cores), the GTX 960 OEM can handle basic tasks in Adobe Premiere Pro or Blender, but rendering complex scenes takes hours. For comparison, the RTX 3050 completes similar tasks 4–5 times faster.

Scientific Calculations

The card supports OpenCL and CUDA, but due to the small number of cores and outdated architecture, its use in machine learning or simulations is limited to educational projects.


5. Power Consumption and Thermal Output

TDP: 120 Watts — A Plus for Older PCs

Modern power supplies can easily handle the GTX 960 OEM. The recommended PSU is 400–450 Watts (e.g., Corsair CX450).

Cooling and Cases

Even OEM versions rarely overheat due to their modest thermal output. A basic cooler and a case with 1-2 fans are sufficient. However, in compact builds, throttling may occur under prolonged load.


6. Comparison with Competitors

AMD Radeon R9 380 (2015)

A close competitor from 2015. The R9 380 outperforms the GTX 960 OEM by 10–15% in games but consumes 190 Watts compared to 120 Watts. By 2025, both cards are equally outdated.

Modern Analogues: NVIDIA RTX 2050 and AMD RX 6400

New budget models (priced at $150–$200) offer 2-3 times higher performance, support for DLSS/FSR, and 4 GB of GDDR6. The GTX 960 OEM (if found new) costs $80–$100, but even then it falls short against these newer options.


7. Practical Advice

Power Supply: 450 Watts — Sufficient

Even for builds with CPUs like the Core i5-12400F.

Compatibility with Platforms

The card utilizes the PCIe 3.0 x16 interface, which is compatible with modern motherboards. However, NVIDIA drivers for the GTX 900 series are updated infrequently — there may be issues with Windows 12 and new games.

Drivers: Look for Optimized Builds

The enthusiast community provides modified drivers (e.g., “NVCleanstall”) that improve compatibility with new software.


8. Pros and Cons

Pros:

- Low price ($80–$100 for new units).

- Energy efficiency (suitable for upgrading old PCs).

- Quiet operation even under load.

Cons:

- Outdated architecture and lack of support for modern technologies.

- Insufficient video memory for games in 2025.

- Limited compatibility with new software.


9. Final Conclusion: Who Is GTX 960 OEM Suitable For?

This graphics card is a choice for:

1. Owners of old PCs looking to breathe new life into their system without replacing the power supply.

2. Retro game enthusiasts (for example, projects from the 2010s).

3. Office builds with rare rendering tasks.

However, if your budget allows for $150–$200, it's better to opt for the RTX 2050 or RX 6400 — they will provide a better future-proof option. The GTX 960 OEM in 2025 remains a niche solution for those who prioritize cost over performance.

Basic

Label Name
NVIDIA
Platform
Desktop
Launch Date
November 2015
Model Name
GeForce GTX 960 OEM
Generation
GeForce 900
Base Clock
1176MHz
Boost Clock
1201MHz
Bus Interface
PCIe 3.0 x16
Transistors
2,940 million
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.
64
Foundry
TSMC
Process Size
28 nm
Architecture
Maxwell 2.0

Memory Specifications

Memory Size
4GB
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.
128bit
Memory Clock
1753MHz
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.
112.2 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.
38.43 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.
76.86 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.
76.86 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.
2.509 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.
1024
L1 Cache
48 KB (per SMM)
L2 Cache
1024KB
TDP
Unknown
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.
1.3
OpenCL Version
3.0
OpenGL
4.6
DirectX
12 (12_1)
CUDA
5.2
Power Connectors
None
Shader Model
6.7
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
200W

Benchmarks

FP32 (float)
Score
2.509 TFLOPS

Compared to Other GPU

FP32 (float) / TFLOPS
2.581 +2.9%
2.415 -3.7%
2.383 -5%