NVIDIA GeForce GTX 980

NVIDIA GeForce GTX 980

NVIDIA GeForce GTX 980 in 2025: Is It Worth Considering the Legend of the Past?

Introduction

The NVIDIA GeForce GTX 980 is a legendary graphics card released in 2014. Despite its venerable age, it can still be found in the PCs of enthusiasts. But is it still relevant in 2025? Let's see who this GPU is suitable for and what tasks it can handle in the era of ray tracing and neural network technologies.


1. Architecture and Key Features

Maxwell Architecture: Humble, Yet Efficient

The GTX 980 is built on the Maxwell architecture (GM204), created using a 28-nm manufacturing process. This was a step forward compared to the previous Kepler generation: energy efficiency increased by 30%, and performance per watt doubled.

Lack of Modern Technologies

The card does not support ray tracing (RTX), DLSS, or FidelityFX Super Resolution (FSR). In 2025, this is a key drawback: most games require hardware acceleration for RT effects, and upscaling has become standard for 4K. However, basic features such as NVIDIA Adaptive V-Sync and DSR (Dynamic Super Resolution) are present.


2. Memory: Volume and Bandwidth

GDDR5: Classic, but Not High-End

The GTX 980 is equipped with 4 GB of GDDR5 memory and a 256-bit bus. The bandwidth is 224 GB/s. In comparison, modern entry-level cards (e.g., RTX 4050) use GDDR6 with bandwidth starting from 360 GB/s.

Impact on Performance

4 GB of video memory is critically insufficient for games in 2025, even at medium settings in 1080p. For instance, in Cyberpunk 2077: Phantom Liberty or Starfield at Ultra textures, FPS drops occur due to buffer overflow. However, for projects from 2015 to 2020 (like The Witcher 3 or GTA V), this amount is adequate.


3. Gaming Performance

1080p: Acceptable for Older Games

In Full HD, the GTX 980 shows decent results:

- The Witcher 3 (Ultra, without HairWorks): 60–70 FPS.

- Fortnite (Epic, without RT): 45–55 FPS.

- CS2 (High): 120–140 FPS.

1440p and 4K: Not for Modern Projects

At 1440p, the average FPS in new games drops to 25–35 frames (e.g., Horizon Forbidden West on Medium). 4K mode is suitable for less demanding indie projects or streaming via GeForce NOW.

Ray Tracing: Lack of Support

RT effects are unavailable as Maxwell does not have hardware RT Core blocks. In games with software emulation (like Quake II RTX), performance drops below 10 FPS.


4. Professional Tasks

CUDA: Basic Capabilities

The card has 2048 CUDA cores. For editing in DaVinci Resolve or Premiere Pro, it is sufficient for working on Full HD projects, but rendering 4K will take 3–4 times longer than on an RTX 3050.

3D Modeling and Scientific Calculations

In Blender or Autodesk Maya, the GTX 980 can handle simple scenes, but Cycles Render will be slow. For machine learning or scientific simulations, it's better to choose cards with Tensor Core support (Ampere or Ada Lovelace).


5. Power Consumption and Heat Generation

TDP of 165W: Modest for 2025

Modern mid-range GPUs (RTX 4060) have a similar TDP but offer higher performance. The recommended power supply is 500W with an 8-pin cable.

Cooling and Cases

The reference NVIDIA cooler (turbo fan) is noisy under load (up to 38 dB). For quieter operation, it’s better to choose models with custom coolers (e.g., MSI Twin Frozr). The case should have good ventilation: at least 2 intake fans and 1 exhaust fan.


6. Comparison with Competitors

Against AMD Radeon R9 390 (2015)

The GTX 980 wins in energy efficiency (165W vs. 275W for R9 390) but loses in memory volume (4 GB vs. 8 GB). In DX12 games, the R9 390 sometimes outperforms Maxwell due to asynchronous computations.

Against Modern Budget GPUs

- NVIDIA RTX 3050 (2022): 2–3 times faster in games, supports DLSS and RT, 8 GB GDDR6. Price: $250.

- AMD RX 6600 (2021): Better optimized for Vulkan, 8 GB GDDR6, FSR 2.0. Price: $220.


7. Practical Tips

Power Supply

Minimum 500W with an 80+ Bronze certification. Examples: Corsair CX550M, EVGA 500 BQ.

Compatibility with Platforms

- PCIe 3.0 x16: Compatible with PCIe 4.0/5.0 motherboards, but bandwidth is limited.

- Drivers: NVIDIA support was discontinued in 2024. The last stable version is 552.44.

Settings Optimization

In games of 2025, disable:

- Volumetric post-effects (Motion Blur, Depth of Field).

- Ultra textures (choose Medium or High).

- Anti-aliasing above FXAA.


8. Pros and Cons

Pros:

- Low price on the secondary market ($70–100).

- Energy efficiency for its class.

- Quiet operation in custom versions.

Cons:

- No support for RTX/DLSS.

- Only 4 GB of video memory.

- Outdated drivers.


9. Conclusion: Who is the GTX 980 For?

This graphics card is a viable option for:

1. Budget Builds: If you need a PC for office tasks and older games.

2. Temporary Solutions: While you save for an RTX 5060.

3. Retro Gamers: To run projects from the 2010s at max settings.

Why Not to Get the GTX 980 in 2025?

Even budget newcomers like the Intel Arc A580 ($150) offer more memory, support for modern APIs, and upscaling technologies.


Conclusion

The NVIDIA GeForce GTX 980 is a respected veteran, but time spares no legend. In 2025, it should only be considered as a stopgap solution or part of a nostalgic build. For comfortable gaming in new releases, look towards GPUs with 8+ GB of memory and support for FSR 3.0 or DLSS 3.5.

Basic

Label Name
NVIDIA
Platform
Desktop
Launch Date
September 2014
Model Name
GeForce GTX 980
Generation
GeForce 900
Base Clock
1127MHz
Boost Clock
1216MHz
Bus Interface
PCIe 3.0 x16
Transistors
5,200 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.
128
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.
256bit
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.
224.4 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.
77.82 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.
155.6 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.
155.6 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.
5.081 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
48 KB (per SMM)
L2 Cache
2MB
TDP
165W
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
2x 6-pin
Shader Model
6.4
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.
64
Suggested PSU
450W

Benchmarks

Shadow of the Tomb Raider 2160p
Score
18 fps
Shadow of the Tomb Raider 1440p
Score
34 fps
Shadow of the Tomb Raider 1080p
Score
63 fps
GTA 5 2160p
Score
59 fps
GTA 5 1440p
Score
61 fps
GTA 5 1080p
Score
98 fps
FP32 (float)
Score
5.081 TFLOPS
3DMark Time Spy
Score
4250
Blender
Score
343.23
Vulkan
Score
38993
OpenCL
Score
29769
Hashcat
Score
196096 H/s

Compared to Other GPU

Shadow of the Tomb Raider 2160p / fps
39 +116.7%
26 +44.4%
1 -94.4%
Shadow of the Tomb Raider 1440p / fps
95 +179.4%
75 +120.6%
54 +58.8%
Shadow of the Tomb Raider 1080p / fps
141 +123.8%
107 +69.8%
79 +25.4%
GTA 5 2160p / fps
146 +147.5%
68 +15.3%
27 -54.2%
GTA 5 1440p / fps
153 +150.8%
103 +68.9%
82 +34.4%
GTA 5 1080p / fps
213 +117.3%
136 +38.8%
FP32 (float) / TFLOPS
5.222 +2.8%
5.147 +1.3%
4.931 -3%
4.864 -4.3%
3DMark Time Spy
7842 +84.5%
1879 -55.8%
Blender
1506.77 +339%
848 +147.1%
45.58 -86.7%
Vulkan
98446 +152.5%
69708 +78.8%
40716 +4.4%
5522 -85.8%
OpenCL
71022 +138.6%
51251 +72.2%
14826 -50.2%
9741 -67.3%
Hashcat / H/s
204331 +4.2%
204127 +4.1%
189947 -3.1%
175982 -10.3%