Home / NVIDIA / NVIDIA NVS 810: Performance and Specs

NVIDIA NVS 810

NVIDIA NVS 810 in 2025: A Professional Tool for Multitasking

Overview of capabilities, performance, and target audience

Introduction

The NVIDIA NVS 810 is a specialized graphics card designed for the corporate and professional sector. Despite its initial release back in 2016, it remains sought after in niche scenarios where support for multiple displays and stable performance is critically important. In this article, we will explore its features, strengths, and weaknesses, as well as identify the audience it serves in an era dominated by gaming GPUs.

Architecture and Key Features

Maxwell Architecture: Time-Tested

The NVS 810 is based on the Maxwell architecture (GM107), manufactured using a 28nm process. This solution does not belong to modern lineups like Ada Lovelace or Ampere, explaining its lack of support for ray tracing (RTX), DLSS, or FidelityFX. However, its key feature is the ability to connect 8 independent displays via DisplayPort 1.2, which is relevant for digital signage, trade terminals, and workstations with multi-monitor configurations.

Unique Features:

- NVIDIA Mosaic Technology — enabling multiple monitors to create a single workspace.

- Support for 4K at 60 Hz on each of the 8 outputs (with limitations due to memory type).

- Optimized for professional NVIDIA drivers, ensuring stability in corporate environments.

Memory: Modest but Sufficient for Tasks

Type and Capacity:

The NVS 810 is equipped with 4 GB of DDR3 memory, distributed across two GPUs on a single board. The memory operates at a frequency of 1800 MHz with a bandwidth of 28.8 GB/s (for each chip). While this is insufficient for modern gaming or 8K rendering, it is acceptable for outputting images across 8 displays in office applications.

Impact on Performance:

- Slow DDR3 restricts graphical performance at high resolutions.

- For tasks like video editing or 3D modeling, the amount of memory is only sufficient for basic projects.

Gaming Performance: Not the Primary Goal

Real-world FPS Figures (1080p, Low Settings):

- CS2: 35–45 FPS.

- Fortnite: 25–30 FPS.

- Cyberpunk 2077: 10–15 FPS (without ray tracing).

Conclusions:

- The card is not intended for gaming — the lack of support for DirectX 12 Ultimate and modern APIs limits compatibility.

- Ray tracing and DLSS are unavailable due to architectural constraints.

Professional Tasks: Where the NVS 810 Shines

Video Editing and 2D Graphics:

- Editing in Adobe Premiere Pro or DaVinci Resolve is possible at resolutions up to 1080p, but rendering will take longer due to the small number of CUDA cores (2× 768 cores).

- Recommended for editing advertisements or presentations, but not for 4K projects.

3D Modeling:

- In Blender or AutoCAD, the card can handle simple scenes, but for complex objects, a discrete Quadro or GeForce RTX is required.

Scientific Calculations:

- Support for CUDA and OpenCL allows the NVS 810 to be used for basic computations, but its performance lags behind even budget gaming GPUs.

Power Consumption and Thermal Output

TDP and Recommendations:

- The card has a TDP of 68 W, powered via the PCIe slot (no additional connectors are required).

- Passive cooling (in some variants, a single fan) makes it ideal for quiet PCs.

- A case with basic ventilation and a power supply of at least 300 W will be suitable for the build.

Comparison with Competitors

AMD FirePro W600 (2014):

- 6 DisplayPort outputs, 4 GB GDDR5.

- Lags behind the NVS 810 in the number of displays but excels in memory speed.

NVIDIA Quadro P620 (2020):

- 4 GB GDDR5, supports 4 displays.

- Better suited for 3D modeling but more expensive ($200 vs. $450 for a new NVS 810 in 2025).

Conclusion: The NVS 810 is a niche solution for those prioritizing the number of monitors over raw performance.

Practical Tips

1. Power Supply: A 300–400 W power supply with an 80+ Bronze certification will suffice.

2. Compatibility: The card operates on PCIe 3.0 x16 and is compatible with modern motherboards.

3. Drivers: Use NVIDIA Studio Drivers for stability in professional applications.

4. OS: Support for Windows 10/11 and Linux (with limited functionality).

Pros and Cons

✅ Pros:

- Supports 8 displays.

- Low power consumption and quiet operation.

- Reliability for corporate solutions.

❌ Cons:

- Weak performance in games and 3D applications.

- Outdated architecture and type of memory.

- High price ($450) for its capabilities.

Final Verdict: Who is the NVS 810 for?

This graphics card is a choice for businesses rather than enthusiasts. It is ideal for:

- Digital advertising billboards and information panels.

- Offices that require connecting 4–8 monitors for trading or video surveillance.

- A temporary solution for basic workstations with a limited budget.

However, if you need power for gaming, rendering, or machine learning, consider the NVIDIA RTX A2000 or AMD Radeon Pro W6600. The NVS 810 remains a niche tool, whose advantages are revealed only in specific scenarios.

Prices are current as of April 2025. The device is available in new builds on order through NVIDIA's partner channels.

Basic

Label Name

NVIDIA

Platform

Desktop

Launch Date

November 2015

Model Name

NVS 810

Generation

NVS

Base Clock

902MHz

Boost Clock

1033MHz

Bus Interface

PCIe 3.0 x16

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.

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.

16.53 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.

33.06 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.

33.06 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.

1.037 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

1024KB

TDP

68W

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

Power Connectors

None

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.

Suggested PSU

250W

Benchmarks

FP32 (float)

Score

1.037 TFLOPS

Compared to Other GPU

FP32 (float) / TFLOPS

Quadro K3100M

1.106 +6.7%

T400

1.072 +3.4%

NVS 810

1.037

Quadro 6000 SDI

1.007 -2.9%

Radeon Vega 6 Embedded

1.003 -3.3%