NVIDIA GeForce GTX 960M

NVIDIA GeForce GTX 960M

NVIDIA GeForce GTX 960M in 2025: Is it Worth Using an Outdated Mobile GPU?

Analysis of the capabilities and relevance of the legendary laptop card


1. Architecture and Key Features

Maxwell Architecture: A Legacy from 2015

The NVIDIA GeForce GTX 960M is based on the Maxwell architecture (GM107), released in 2015. The manufacturing process is 28 nm, which seems archaic in 2025 compared to 5–7 nm chips in modern GPUs. The card does not support key technologies from recent years: ray tracing (RTX), DLSS, FidelityFX, or hardware-accelerated AI. Its main advantage is energy efficiency optimization for laptops, but this is not sufficient for modern tasks.

Unique Features?

Unfortunately, there are none. The GTX 960M operates at a basic level: it supports DirectX 12 (Feature Level 11_0), OpenGL 4.5, and Vulkan 1.1. Attempts to run RTX effects through emulation (for example, in projects with software ray tracing) result in FPS dropping below 10 frames.


2. Memory: The Weak Link

GDDR5 and Narrow Bus

The memory volume is either 2 or 4 GB GDDR5 with a 128-bit bus. The bandwidth is 80 GB/s (for comparison, the RTX 4050 Mobile has a 192-bit bus and 336 GB/s). In games of 2025, even 4 GB is insufficient: high-resolution textures and complex shaders consume resources. For example, in Cyberpunk 2077: Phantom Liberty on low settings at 1080p, the graphics card experiences frequent stuttering due to buffer overflow.


3. Gaming Performance: Only Indie and Retro Games

FPS in Popular Titles

- Fortnite (1080p, low settings): 35–45 FPS (without DLSS or FSR support).

- Counter-Strike 2 (1080p, medium settings): 60–70 FPS.

- Hogwarts Legacy (720p, low settings): 20–25 FPS.

4K? Even 1440p is an uphill struggle. In League of Legends (1440p), FPS will drop to 40–50 due to memory and computational power limitations.


4. Professional Tasks: Minimal Usability

CUDA and OpenCL

The GTX 960M has 640 CUDA cores. For rendering in Blender or editing in DaVinci Resolve, it is sufficient only for simple projects. For instance, rendering a scene of medium complexity will take 3–4 times longer than on an RTX 3050. In scientific calculations (e.g., MATLAB), the card lags behind even integrated GPUs in Ryzen 7000.


5. Power Consumption and Heat Output

TDP 65W: Light but Inefficient

At 65W, it is considered modest by 2025 standards, but the efficiency of Maxwell lags behind modern GPUs. In laptops with a GTX 960M, maintenance is critical: thermal paste needs to be replaced every 1–2 years, and fans need to be cleaned. When overheating (above 90°C), the card throttles, losing up to 30% of its performance.


6. Comparison with Competitors

Market 2015–2016: AMD Radeon R9 M380

The main competitor to the GTX 960M at the time was the Radeon R9 M380 (GCN 3.0 architecture). Both cards showed similar performance, but NVIDIA's drivers proved to be more stable. By 2025, both models are equally outdated.

Modern Analogues: Intel Arc A350M (2022) and AMD Radeon 7600S (2023) outperform the GTX 960M by 3–4 times while maintaining similar TDP.


7. Practical Advice

Power Supply and Compatibility

- A standard adapter (120–150W) is sufficient for laptops with a GTX 960M.

- OS Compatibility: NVIDIA's official drivers have been updated until 2023. In Windows 11, conflicts may occur — it’s better to use modified community drivers.

Important: Don't expect to connect external 4K 60Hz monitors — HDMI 2.0 is absent.


8. Pros and Cons

Pros:

- Low power consumption.

- Support for basic games and applications.

- Availability in the secondary market (used price — $50–80).

Cons:

- No support for modern technologies (RTX, DLSS, AV1).

- Limited memory.

- Outdated interfaces (HDMI 1.4, DisplayPort 1.2).


9. Final Conclusion: Who is GTX 960M Suitable For?

This card is geared towards:

- Owners of old laptops looking to extend their lifespan for office tasks, video watching, and running light games (like Stardew Valley or Among Us).

- Students learning the basics of 3D modeling at a fundamental level.

- Retro gaming enthusiasts playing games from the early 2010s.

Why Look Towards New GPUs?

Even budget models in 2025 (like the RTX 3050 Mobile or Intel Arc A580) offer 4–5 times higher performance, support for AI technologies, and up-to-date interfaces. Prices for new laptops with such cards start at $600, making the GTX 960M a niche solution.


Summary: The GTX 960M in 2025 is a "workhorse" for very specific scenarios. If you are not ready to deal with compromises, invest in modern hardware.

Basic

Label Name
NVIDIA
Platform
Mobile
Launch Date
March 2015
Model Name
GeForce GTX 960M
Generation
GeForce 900M
Base Clock
1097MHz
Boost Clock
1176MHz
Bus Interface
MXM-B (3.0)
Transistors
1,870 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.
40
Foundry
TSMC
Process Size
28 nm
Architecture
Maxwell

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
1253MHz
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.
80.19 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.
18.82 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.
47.04 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.
47.04 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.
1.475 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.
640
L1 Cache
64 KB (per SMM)
L2 Cache
2MB
TDP
75W
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 (11_0)
CUDA
5.0
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.
16

Benchmarks

FP32 (float)
Score
1.475 TFLOPS
3DMark Time Spy
Score
1205
Blender
Score
81
OctaneBench
Score
31
Vulkan
Score
10184
OpenCL
Score
11180
Hashcat
Score
62554 H/s

Compared to Other GPU

FP32 (float) / TFLOPS
1.598 +8.3%
1.535 +4.1%
3DMark Time Spy
5182 +330%
3906 +224.1%
2755 +128.6%
1769 +46.8%
Blender
1497 +1748.1%
194 +139.5%
OctaneBench
123 +296.8%
69 +122.6%
Vulkan
98446 +866.7%
69708 +584.5%
40716 +299.8%
18660 +83.2%
OpenCL
62821 +461.9%
38843 +247.4%
21442 +91.8%
11291 +1%
Hashcat / H/s
65496 +4.7%
63227 +1.1%
59644 -4.7%
59020 -5.6%