NVIDIA GeForce 940M

NVIDIA GeForce 940M

NVIDIA GeForce 940M: Review of an Outdated Yet Still Viable Mobile Graphics Card

(Relevant as of April 2025)

Despite being a decade-old mobile graphics card, the NVIDIA GeForce 940M is still found in older laptops and budget devices. In this article, we will explore what this GPU is capable of in 2025, whom it might suit, and what limitations should be considered.


1. Architecture and Key Features

Maxwell Architecture: A Modest Legacy

The GeForce 940M is built on the Maxwell (GM108) architecture, released in 2014. This was NVIDIA's first generation to place a strong emphasis on energy efficiency. The manufacturing process is 28 nm, which seems archaic by today's standards (where 4–5 nm processes dominate).

Unique Features: There Are Almost None

The card does not support modern technologies like RTX (ray tracing), DLSS (AI upscaling), or FidelityFX (AMD optimization). Its main feature is Optimus, which automatically switches between integrated and discrete graphics for power saving.


2. Memory: Modest Specs

Type and Amount

The 940M uses DDR3 or GDDR5 (depending on the version) with a capacity of 2–4 GB. The bus width is 128 bits, and the bandwidth reaches 40–80 GB/s (for GDDR5). For comparison, even a budget RTX 4050 (2023) has 96 GB/s thanks to GDDR6.

Impact on Performance

The memory capacity is sufficient for basic tasks (office, browser), but it becomes a bottleneck in gaming and professional applications. For instance, textures in modern projects (like Cyberpunk 2077) take up 4–6 GB, leading to FPS drops even at low settings.


3. Gaming Performance: Nostalgia for the 2010s

Average FPS in Popular Games

- CS2 (2023): 25–35 FPS on low settings at 720p.

- Fortnite: 20–30 FPS (720p, low detail).

- The Witcher 3 (2015): 22–28 FPS (720p, minimum settings).

- Dota 2: 40–50 FPS (1080p, medium settings).

Resolutions and Ray Tracing

The card is meant for 720p–1080p, but in 2025, comfortable gaming is only possible in older projects or indie games (Hollow Knight, Stardew Valley). There is no support for ray tracing—this is exclusively the domain of the RTX series.


4. Professional Tasks: Minimal Capabilities

Video Editing and 3D Modeling

With CUDA (384 cores), the 940M can handle simple edits in Adobe Premiere Pro or DaVinci Resolve, but rendering 4K video will take hours. For Blender or AutoCAD, the card is only suitable for learning or working on small projects.

Scientific Calculations

Its use in scientific tasks (e.g., machine learning) is limited due to the small number of cores and lack of support for modern APIs.


5. Power Consumption and Heat Dissipation

TDP and Cooling

The card has a TDP of 33–45 W, allowing it to be used in slim laptops with passive or compact active cooling. However, under prolonged loads, overheating is possible (up to 85–90°C), which can reduce the lifespan of the device.

Recommendations

- Regularly clean the cooling system from dust.

- Use cooling pads for laptops.

- Avoid gaming and rendering on your lap—this worsens ventilation.


6. Comparison with Competitors

Analogues from 2015–2017:

- AMD Radeon R7 M360: Falls behind the 940M in energy efficiency but has similar performance.

- Intel HD Graphics 620: Integrated graphics that are 30–40% weaker in games.

In 2025:

Even budget mobile GPUs like the AMD Radeon 780M (integrated in Ryzen 8000) or Intel Arc A350M outperform the 940M by 3–5 times.


7. Practical Tips

Power Supply

For laptops with a 940M, a standard adapter (65–90 W) is sufficient. When upgrading other components (e.g., SSD), ensure that the power supply maintains a reserve capacity.

Compatibility

- Platforms: The card works only in laptops with Intel 4-8 generation chipsets or AMD A10–FX.

- Drivers: The latest NVIDIA driver versions for the 940M were released in 2023. Windows 11 may present conflicts—use compatibility mode.


8. Pros and Cons

Pros:

- Low power consumption.

- Quiet operation in office scenarios.

- Support for DirectX 12 (without advanced features).

Cons:

- Not suitable for modern games and applications.

- Limited driver support.

- No RTX/DLSS technologies.


9. Final Conclusion: Who Is the GeForce 940M Suitable for in 2025?

This graphics card is suitable for:

1. Owners of old laptops who need to run office applications, a browser, or retro games.

2. Students for working with documents and simple software.

3. Enthusiasts building budget PCs from used components.

However, for gaming, video editing, or 3D modeling in 2025, the 940M is hopelessly outdated. If your budget is limited to $300–400, consider laptops with integrated graphics like the Ryzen 5 8600G or Intel Core Ultra 5—since their performance is significantly higher.


Conclusion

The GeForce 940M is an example of a "workhorse" that has outlived its prime but can still be useful in specific scenarios. However, in an era of AI accelerators and 4K gaming, its time has irretrievably passed.

Basic

Label Name
NVIDIA
Platform
Mobile
Launch Date
March 2015
Model Name
GeForce 940M
Generation
GeForce 900M
Base Clock
1020MHz
Boost Clock
1098MHz
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.
32
Foundry
TSMC
Process Size
28 nm
Architecture
Maxwell

Memory Specifications

Memory Size
2GB
Memory Type
DDR3
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.
64bit
Memory Clock
900MHz
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.
14.40 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.
17.57 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.
35.14 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.
35.14 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.
1.102 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.
512
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
1.102 TFLOPS
Vulkan
Score
5522
OpenCL
Score
6073
Hashcat
Score
36824 H/s

Compared to Other GPU

FP32 (float) / TFLOPS
1.16 +5.3%
1.131 +2.6%
1.102
1.067 -3.2%
Vulkan
98446 +1682.8%
69708 +1162.4%
40716 +637.3%
18660 +237.9%
OpenCL
62821 +934.4%
38843 +539.6%
21442 +253.1%
11291 +85.9%
Hashcat / H/s
40676 +10.5%
38717 +5.1%
36824
36798 -0.1%
35068 -4.8%