NVIDIA GeForce GTX 950 Low Power

NVIDIA GeForce GTX 950 Low Power

NVIDIA GeForce GTX 950 Low Power: A Compact Veteran in 2025

Introduction

The NVIDIA GeForce GTX 950 Low Power (LP) is a graphics card released in 2015, still found in budget builds today. Despite its venerable age, its low power consumption and compactness remain relevant for specific scenarios. This article will explore who might benefit from this card in 2025 and what compromises one would need to make.


Architecture and Key Features

Maxwell Architecture: Simplicity and Efficiency

The GTX 950 LP is built on the Maxwell architecture (GM206), manufactured using a 28nm process. This generation focused on optimizing energy efficiency, particularly evident in the Low Power version.

Lack of Modern Features

The card does not support ray tracing (RTX), DLSS, or FidelityFX. There are no tensor or RT cores—just classic CUDA cores (768 in total) and basic technologies like NVIDIA Adaptive Vertical Sync.

Low Power Feature

The LP variant features a reduced TDP (up to 75W) due to lowered clock speeds. This allows it to operate without additional power through a 6-pin connector, which is rare even among modern budget GPUs.


Memory: A Modest Yet Crucial Resource

GDDR5 and 2 GB: Minimum for 2025

The GTX 950 LP is equipped with 2 GB of GDDR5 memory on a 128-bit bus. The bandwidth is 105.6 GB/s. For modern games, this capacity is insufficient; even in Fortnite or CS2 at medium settings, there are likely to be slowdowns due to a lack of VRAM.

Impact on Performance

In games from the 2010s (e.g., The Witcher 3 or GTA V), the card demonstrates 40-50 FPS on medium settings at 1080p. However, projects from 2023-2025, like Cyberpunk 2077: Phantom Liberty, will only run on low presets at around 20-25 FPS.


Gaming Performance: Realistic Expectations

1080p: Basic Level

- Dota 2: 60-70 FPS (medium settings).

- Apex Legends: 35-45 FPS (low settings).

- Elden Ring: 25-30 FPS (minimum graphics).

1440p and 4K: Not for This Card

Even in less demanding games (e.g., Hollow Knight), resolutions higher than 1080p will lead to a drop in FPS. 4K mode is out of the question due to a lack of memory and computational power.

Ray Tracing: No Support

RTX features are unavailable. For comparison, even the GTX 1650 with 4 GB of GDDR5 performs better thanks to support for modern APIs.


Professional Tasks: Limited Applicability

Video Editing and Rendering

In Premiere Pro or DaVinci Resolve, the card will accelerate rendering through CUDA, but 2 GB of memory will become a bottleneck when working with 4K materials. It is only suitable for editing in 1080p.

3D Modeling

Blender or Maya will run, but complex scenes will be processed slowly. It is acceptable for educational projects or simple models but not for professional work.

Scientific Calculations (CUDA/OpenCL)

CUDA 5.2 support allows the card to be used in machine learning for basic experiments; however, operation speeds are vastly inferior to modern GPUs.


Power Consumption and Thermal Output

TDP 75W: Energy Efficiency First

The card does not require additional power and is satisfied with the PCIe slot. This makes it ideal for upgrading old PCs with weak power supplies.

Cooling and Cases

Passive or single-slot active coolers ensure quiet operation. The maximum temperature under load is 70-75°C. It can even fit into mini-ITX cases with limited ventilation.


Comparison with Competitors

Analogues from 2015-2017

- AMD Radeon R7 370: 2 GB GDDR5, similar performance, but TDP of 110W.

- NVIDIA GTX 1050 (2 GB): 30% faster but requires 75W and is more expensive on the secondary market ($80-100 versus $50-70 for GTX 950 LP).

Modern Budget Models (2025)

- Intel Arc A310: 4 GB GDDR6, ray tracing support, priced at $120-150.

- AMD Radeon RX 6400: 4 GB GDDR6, 53W TDP, with performance 2-3 times higher.


Practical Tips

Power Supply: 300W Enough

Even for systems with processors like the Core i5-10400 or Ryzen 5 3600.

Platform Compatibility

- Motherboards: PCIe 3.0 x16 (backward compatible with PCIe 2.0).

- OS: Windows 10/11 (drivers available until 2021). Linux support through open-source drivers Nouveau is limited.

Driver Nuances

Official updates stopped in 2021. There may be bugs or a lack of optimizations in newer games.


Pros and Cons

Pros:

- Low power consumption.

- Compact size and quiet operation.

- CUDA support for basic tasks.

- Affordable price on the secondary market ($50-70).

Cons:

- Only 2 GB of video memory.

- Lack of support for modern technologies (DLSS, Ray Tracing).

- Poor performance in new games.


Final Verdict: Who Is the GTX 950 LP For?

This graphics card is suitable for:

1. Owners of Old PCs who need an upgrade without replacing the power supply.

2. HTPC Builders for video playback and light gaming.

3. Students learning the basics of 3D modeling on simple projects.

4. Retro gaming enthusiasts, where the power is sufficient for comfortable FPS.

In 2025, the GTX 950 LP is a niche solution. If your budget is capped at $100, it’s better to consider a used GTX 1050 Ti or a new Intel Arc A310. However, for specific tasks where compactness and minimal power consumption are crucial, this card can still serve its purpose.

Basic

Label Name
NVIDIA
Platform
Desktop
Launch Date
March 2016
Model Name
GeForce GTX 950 Low Power
Generation
GeForce 900
Base Clock
1026MHz
Boost Clock
1190MHz
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.
48
Foundry
TSMC
Process Size
28 nm
Architecture
Maxwell 2.0

Memory Specifications

Memory Size
2GB
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
1653MHz
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.
105.8 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.
38.08 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.
57.12 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.
57.12 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.
1.865 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.
768
L1 Cache
48 KB (per SMM)
L2 Cache
1024KB
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 (12_1)
CUDA
5.2
Power Connectors
None
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.
32
Suggested PSU
250W

Benchmarks

FP32 (float)
Score
1.865 TFLOPS
Blender
Score
142
OctaneBench
Score
45

Compared to Other GPU

FP32 (float) / TFLOPS
1.819 -2.5%
1.756 -5.8%
Blender
1506.77 +961.1%
848 +497.2%
194 +36.6%