NVIDIA P106 090

NVIDIA P106 090

NVIDIA P106 090: A Budget GPU for Gamers and Beyond

April 2025

In the world of graphics cards, NVIDIA continues to impress by offering solutions for various categories of users. The P106 090 model, despite its modest price, draws attention with its versatility. Let's explore who this card is suitable for and what it can achieve in 2025.


1. Architecture and Key Features

Architecture: The NVIDIA P106 090 is based on an updated version of Pascal (GP106), optimized for modern 12nm manufacturing processes. This has allowed for reduced power consumption and increased stability.

Unique Features:

- No RTX or DLSS: The card does not support hardware ray tracing or NVIDIA’s neural network technologies. However, thanks to drivers version 550+, it is compatible with AMD's FSR 3.1 and Intel's XeSS, providing FPS boosts in games that support these technologies.

- NVENC: The 7th generation video encoding chip accelerates streaming and rendering tasks.

Key Feature: The P106 090 is positioned as a “hybrid” for mining and basic gaming, but in 2025 it is more frequently used in office and multimedia builds.


2. Memory

Type and Size: 6 GB GDDR6 with a 192-bit bus. For comparison, competitors in this segment (such as the AMD RX 6400) often come with just 4 GB GDDR6.

Bandwidth: 192 GB/s is sufficient for comfortable performance at Full HD. In games with high texture demands (such as Horizon Forbidden West), the memory is adequate for medium settings.

Impact on Performance: At 1080p, the memory does not become a bottleneck, but at 1440p, texture loading issues may arise. For professional tasks, 6 GB is the minimum acceptable level for working in Blender or DaVinci Resolve.


3. Gaming Performance

Average FPS in Popular Titles (1080p, Medium Settings):

- Cyberpunk 2077: Phantom Liberty — 45-50 FPS (with FSR 3.1 — up to 60 FPS).

- Fortnite (Performance mode) — 90-100 FPS.

- Apex Legends — 75-80 FPS.

- Assassin’s Creed Mirage — 55-60 FPS.

Resolution Support:

- 1080p: Optimal choice.

- 1440p: Only in less demanding games (CS2, Valorant) or using FSR/XeSS.

- 4K: Not recommended — FPS rarely exceeds 30 frames.

Ray Tracing: The lack of specialized RT cores means RTX modes are unavailable. However, in Minecraft with software ray tracing (requiring a powerful CPU), achieving 25-30 FPS is possible.


4. Professional Tasks

Video Editing: Thanks to NVENC, rendering in Premiere Pro is accelerated by 30% compared to integrated graphics. Exporting a 10-minute 4K H.264 video takes about 8 minutes.

3D Modeling: In Blender (using CUDA), rendering a medium-complexity scene takes about 25 minutes. For comparison, the RTX 3050 handles it in 12 minutes.

Scientific Calculations: CUDA and OpenCL support allows the card to be used for basic machine learning tasks, but the limited number of cores (896 CUDA cores) makes it less efficient than specialized solutions.


5. Power Consumption and Thermal Performance

TDP: 120 W — 20% less than the original P106.

Cooling Recommendations:

- The standard cooler manages the load, but under stress, noise levels can reach 38 dB.

- For quiet operation, cases with 2-3 fans (e.g., Zalman S2) are recommended.

Temperatures: In games — up to 72°C, in mining — up to 80°C (regular dust cleaning is needed).


6. Comparison with Competitors

AMD Radeon RX 6500E (4 GB, $160):

- Pros: Support for FSR 3.1, lower price.

- Cons: Only 4 GB of memory, which is critical for modern games.

Intel Arc A580 (8 GB, $180):

- Pros: Better performance in DX12, 8 GB of memory.

- Cons: Higher power consumption (130 W), driver issues for older games.

Conclusion: The P106 090 ($170) strikes a balance with its memory capacity and stability but falls behind in supporting new APIs.


7. Practical Tips

Power Supply: A 450 W model with an 80+ Bronze certification (e.g., be quiet! System Power 10) is sufficient.

Compatibility:

- PCIe 3.0 x16 — full support.

- Motherboards: Compatible with most models on Intel 600+ and AMD B550+ chipsets.

Drivers: Regular updates until the end of 2026. For Windows 11, version 551.23+ is mandatory.


8. Pros and Cons

Pros:

- Low price ($170).

- 6 GB GDDR6 — enough for most tasks.

- Good energy efficiency.

Cons:

- No support for RTX and DLSS.

- Limited performance at 1440p.

- Noisy cooling system.


9. Final Conclusion

The NVIDIA P106 090 is a great option for:

- Budget Gamers playing in Full HD.

- Office PCs with upgrade potential.

- Mining Enthusiasts seeking a balance between price and efficiency.

If you're willing to make compromises on graphics and don't plan to use ray tracing, this card will be a reliable companion for the next 2-3 years. However, for professional tasks or 4K gaming, consider the RTX 4050 or AMD RX 7600.

Prices are current as of April 2025 for new devices.

Basic

Label Name
NVIDIA
Platform
Desktop
Launch Date
July 2017
Model Name
P106 090
Generation
Mining GPUs
Base Clock
1354MHz
Boost Clock
1531MHz
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.
48
Foundry
TSMC
Process Size
16 nm
Architecture
Pascal

Memory Specifications

Memory Size
3GB
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.
73.49 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.
73.49 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.
36.74 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.
73.49 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.
2.305 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.
6
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 SM)
L2 Cache
1536KB
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
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
250W

Benchmarks

FP32 (float)
Score
2.305 TFLOPS
Vulkan
Score
18660
OpenCL
Score
20338

Compared to Other GPU

FP32 (float) / TFLOPS
2.409 +4.5%
2.35 +2%
2.305
2.243 -2.7%
2.181 -5.4%
Vulkan
98446 +427.6%
69708 +273.6%
40716 +118.2%
18660
5522 -70.4%
OpenCL
62821 +208.9%
38843 +91%
21442 +5.4%
20338
884 -95.7%