NVIDIA P106 100

NVIDIA P106 100

NVIDIA P106-100 in 2025: Outdated Fighter or Budget Option?

Let's figure out who this graphics card is suitable for today


Introduction

The NVIDIA P106-100 is an unusual graphics card originally created for cryptocurrency mining, but it has found a second life in the hands of enthusiasts. In 2025, nearly 8 years after its release, it continues to attract attention thanks to its low price and CUDA support. But how relevant is it for gaming and work? Let's delve into the details.


Architecture and Key Features

Foundation: Pascal, tried and true

The P106-100 is built on the Pascal architecture (2016) and manufactured using TSMC’s 16nm technology. At its core is the GP106 chip, similar to the GTX 1060 6GB but with a key distinction: it lacks direct video output via DisplayPort/HDMI. To connect a monitor, integration with processor graphics (e.g., Intel HD) is required.

What can it do, and what can't it?

- No RTX or DLSS: The card does not support ray tracing or AI scaling, as these technologies emerged with Turing (2018) and Ampere (2020).

- Lack of FidelityFX Super Resolution: This AMD technology is incompatible with NVIDIA's hardware.

- CUDA 6.1: Allows the GPU to be used for calculations but falls short compared to modern versions (CUDA 12+).


Memory: Speed and Volume

GDDR5: Modest, but enough?

- Volume: 6GB is acceptable for light tasks but insufficient for 4K textures in 2025 games.

- Bandwidth: 192 GB/s (192-bit bus width, 8 GHz frequency).

- Impact on Performance: In games with high texture settings (e.g., Cyberpunk 2077: Phantom Liberty), there may be drops due to limited speed and capacity.


Gaming Performance

1080p: Minimum for Comfort

At medium settings in 2025, the P106-100 shows modest results:

- Fortnite (DX11): ~45-55 FPS.

- Apex Legends: ~40-50 FPS.

- CS2: ~70-90 FPS.

- The Witcher 3 (Next-Gen Update): ~30-35 FPS.

1440p and 4K: Not recommended. Even at low settings, FPS rarely exceeds 25-30 frames.

Ray Tracing: Not available due to the absence of RT cores.

Tip: Use modified drivers (e.g., "P106-100 Gaming Patch") to unlock full performance.


Professional Tasks

CUDA: The Main Advantage

- Video Editing: In DaVinci Resolve, the card handles rendering for 1080p projects, but for 4K, it’s better to choose modern models.

- 3D Modeling: In Blender (Cycles), rendering a medium-level scene will take 30-40% more time than on an RTX 3050.

- Scientific Calculations: Suitable for basic tasks in MATLAB or TensorFlow, but the lack of FP64 support limits its use.


Power Consumption and Heat Dissipation

TDP 120W: Modest, but needs attention

- Power Supply: Minimum 400W (recommended 500W for reliability).

- Cooling: Most models use a single fan. Under load, the temperature ranges from 70-80°C.

- Case: 2-3 intake and exhaust fans are mandatory. Avoid compact cases without airflow.


Comparison with Competitors

NVIDIA GTX 1650 Super (2020):

- Pros: Official game support, DLSS 1.0, TDP 100W.

- Cons: 4GB GDDR6, price $160-180 (new).

AMD RX 6400 (2023):

- Pros: Support for FSR 3.0, PCIe 4.0, TDP 53W.

- Cons: 4GB GDDR6, limited performance.

Conclusion: The P106-100 only wins in pricing ($100-120), but loses in optimization and features.


Practical Tips

Power Supply: Choose models with an 80+ Bronze certification and overload protection (Corsair CX550, be quiet! System Power 10).

Compatibility:

- Motherboards: Compatible only with Intel processors (4th-8th generation) or AMD APUs (Ryzen 2000G+).

- Drivers: For operation in Windows 11 2025 Update, manual installation of modified drivers is required.

Details:

- No HDMI/DP: Monitor connection through integrated CPU graphics.

- Updates: Official driver support ceased in 2021.


Pros and Cons

Pros:

- Low cost ($100-120).

- CUDA support for computations.

- Sufficient memory for light tasks.

Cons:

- No official support for gaming drivers.

- High power consumption for its class.

- Limited performance in modern projects.


Final Conclusion: Who is the P106-100 suitable for in 2025?

1. Budget Builds: For office PCs or HTPC capable of running older games.

2. Enthusiasts: Those ready to experiment with drivers for unofficial support.

3. CUDA Tasks: Basic rendering or calculations where cost is more important than speed.

Alternative: If the budget allows $150+, it’s better to choose the new Intel Arc A380 or AMD RX 6500 XT — they offer modern features and warranty.


The NVIDIA P106-100 in 2025 is an example of "survived" hardware still finding application. However, its time is running out: without support for new technologies and drivers, it remains a niche solution for those who prioritize price over convenience.

Basic

Label Name
NVIDIA
Platform
Desktop
Launch Date
June 2017
Model Name
P106 100
Generation
Mining GPUs
Base Clock
1506MHz
Boost Clock
1709MHz
Bus Interface
PCIe 3.0 x16
Transistors
4,400 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.
80
Foundry
TSMC
Process Size
16 nm
Architecture
Pascal

Memory Specifications

Memory Size
6GB
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.
192bit
Memory Clock
2002MHz
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.
192.2 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.
82.03 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.
136.7 GTexel/s
FP16 (half)
?
An important metric for measuring GPU performance is floating-point computing capability. Half-precision floating-point numbers (16-bit) are used for applications like machine learning, where lower precision is acceptable. 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.
68.36 GFLOPS
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.
136.7 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.
4.463 TFLOPS

Miscellaneous

SM Count
?
Multiple Streaming Processors (SPs), along with other resources, form a Streaming Multiprocessor (SM), which is also referred to as a GPU's major core. These additional resources include components such as warp schedulers, registers, and shared memory. The SM can be considered the heart of the GPU, similar to a CPU core, with registers and shared memory being scarce resources within the SM.
10
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.
1280
L1 Cache
48 KB (per SM)
L2 Cache
1536KB
TDP
120W
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
6.1
Power Connectors
1x 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.
48
Suggested PSU
300W

Benchmarks

FP32 (float)
Score
4.463 TFLOPS
3DMark Time Spy
Score
4126
Blender
Score
391
Vulkan
Score
31357
OpenCL
Score
34533
Hashcat
Score
175982 H/s

Compared to Other GPU

FP32 (float) / TFLOPS
4.841 +8.5%
4.677 +4.8%
4.463
4.303 -3.6%
3DMark Time Spy
7690 +86.4%
5521 +33.8%
4126
2852 -30.9%
1806 -56.2%
Blender
1506.77 +285.4%
848 +116.9%
391
45.58 -88.3%
Vulkan
69708 +122.3%
40716 +29.8%
31357
5522 -82.4%
OpenCL
74179 +114.8%
56310 +63.1%
34533
16523 -52.2%
9985 -71.1%
Hashcat / H/s
196096 +11.4%
189947 +7.9%
175982
175296 -0.4%
161084 -8.5%