NVIDIA P106-090
NVIDIA graphics card specifications and benchmark scores
At a Glance
NVIDIANVIDIA P106-090 Specifications
P106-090 GPU Core
Shader units and compute resources
The NVIDIA P106-090 GPU core specifications define its raw processing power for graphics and compute workloads. Shading units (also called CUDA cores, stream processors, or execution units depending on manufacturer) handle the parallel calculations required for rendering. TMUs (Texture Mapping Units) process texture data, while ROPs (Render Output Units) handle final pixel output. Higher shader counts generally translate to better GPU benchmark performance, especially in demanding games and 3D applications.
P106-090 Clock Speeds
GPU and memory frequencies
Clock speeds directly impact the P106-090's performance in GPU benchmarks and real-world gaming. The base clock represents the minimum guaranteed frequency, while the boost clock indicates peak performance under optimal thermal conditions. Memory clock speed affects texture loading and frame buffer operations. The P106-090 by NVIDIA dynamically adjusts frequencies based on workload, temperature, and power limits to maximize performance while maintaining stability.
NVIDIA's P106-090 Memory
VRAM capacity and bandwidth
VRAM (Video RAM) is dedicated memory for storing textures, frame buffers, and shader data. The P106-090's memory capacity determines how well it handles high-resolution textures and multiple displays. Memory bandwidth, measured in GB/s, affects how quickly data moves between the GPU and VRAM. Higher bandwidth improves performance in memory-intensive scenarios like 4K gaming. The memory bus width and type (GDDR6, GDDR6X, HBM) significantly influence overall GPU benchmark scores.
P106-090 by NVIDIA Cache
On-chip cache hierarchy
On-chip cache provides ultra-fast data access for the P106-090, reducing the need to fetch data from slower VRAM. L1 and L2 caches store frequently accessed data close to the compute units. AMD's Infinity Cache (L3) dramatically increases effective bandwidth, improving GPU benchmark performance without requiring wider memory buses. Larger cache sizes help maintain high frame rates in memory-bound scenarios and reduce power consumption by minimizing VRAM accesses.
P106-090 Theoretical Performance
Compute and fill rates
Theoretical performance metrics provide a baseline for comparing the NVIDIA P106-090 against other graphics cards. FP32 (single-precision) performance, measured in TFLOPS, indicates compute capability for gaming and general GPU workloads. FP64 (double-precision) matters for scientific computing. Pixel and texture fill rates determine how quickly the GPU can render complex scenes. While real-world GPU benchmark results depend on many factors, these specifications help predict relative performance levels.
Pascal Architecture & Process
Manufacturing and design details
The NVIDIA P106-090 is built on NVIDIA's Pascal architecture, which defines how the GPU processes graphics and compute workloads. The manufacturing process node affects power efficiency, thermal characteristics, and maximum clock speeds. Smaller process nodes pack more transistors into the same die area, enabling higher performance per watt. Understanding the architecture helps predict how the P106-090 will perform in GPU benchmarks compared to previous generations.
NVIDIA's P106-090 Power & Thermal
TDP and power requirements
Power specifications for the NVIDIA P106-090 determine PSU requirements and thermal management needs. TDP (Thermal Design Power) indicates the heat output under typical loads, guiding cooler selection. Power connector requirements ensure adequate power delivery for stable operation during demanding GPU benchmarks. The suggested PSU wattage accounts for the entire system, not just the graphics card. Efficient power delivery enables the P106-090 to maintain boost clocks without throttling.
P106-090 by NVIDIA Physical & Connectivity
Dimensions and outputs
Physical dimensions of the NVIDIA P106-090 are critical for case compatibility. Card length, height, and slot width determine whether it fits in your chassis. The PCIe interface version affects bandwidth for communication with the CPU. Display outputs define monitor connectivity options, with modern cards supporting multiple high-resolution displays simultaneously. Verify these specifications against your case and motherboard before purchasing to ensure a proper fit.
NVIDIA API Support
Graphics and compute APIs
API support determines which games and applications can fully utilize the NVIDIA P106-090. DirectX 12 Ultimate enables advanced features like ray tracing and variable rate shading. Vulkan provides cross-platform graphics capabilities with low-level hardware access. OpenGL remains important for professional applications and older games. CUDA (NVIDIA) and OpenCL enable GPU compute for video editing, 3D rendering, and scientific applications. Higher API versions unlock newer graphical features in GPU benchmarks and games.
P106-090 Product Information
Release and pricing details
The NVIDIA P106-090 is manufactured by NVIDIA as part of their graphics card lineup. Release date and launch pricing provide context for comparing GPU benchmark results with competing products from the same era. Understanding the product lifecycle helps evaluate whether the P106-090 by NVIDIA represents good value at current market prices. Predecessor and successor information aids in tracking generational improvements and planning future upgrades.
P106-090 Benchmark Scores
3dmark_3dmark_steel_nomad_dx12Source
3DMark Steel Nomad is the latest GPU benchmark running at native 4K with DirectX 12. It's roughly 3x more demanding than Time Spy, testing NVIDIA P106-090 with cutting-edge rendering techniques. The benchmark uses state-of-the-art graphics technologies to stress modern hardware. Scores accurately predict NVIDIA P106-090 performance in demanding AAA games at 4K resolution.
Top 5 Performers
Top 5 PerformersNearby Performers
Nearby Performersgeekbench_openclSource
Geekbench OpenCL tests GPU compute performance using the cross-platform OpenCL API. This shows how NVIDIA P106-090 handles parallel computing tasks like video encoding and scientific simulations. OpenCL is widely supported across different GPU vendors and platforms. Higher scores benefit applications that leverage GPU acceleration for non-graphics workloads.
Top 5 Performers
Nearby Performers
geekbench_vulkanSource
Geekbench Vulkan tests GPU compute using the modern low-overhead Vulkan API. This shows how NVIDIA P106-090 performs with next-generation graphics and compute workloads.
Top 5 Performers
Nearby Performers
About NVIDIA P106-090
The NVIDIA P106-090 is a Pascal-architecture mining GPU built on TSMC's 16 nm process, featuring the GP106 chip with 4,400 million transistors on a 200 mm² die. It ships with 3 GB of GDDR5 memory on a 192-bit bus, delivering 192.2 GB/s of bandwidth, and its average benchmark score of 13716 places it at the 54th percentile among all GPUs in the database. This is a dual-slot card with no display outputs, designed exclusively for compute workloads, and its production status is end-of-life, with a release date of July 30, 2017.
Benchmark Performance
The benchmark results for the P106-090 show a GPU that sits in a narrow competitive band, with its average score of 13716 placing it within roughly one percent of all four nearest rivals. In the 3DMark Steel Nomad DX12 test, the card scores 509 points, which is a modest result that reflects its mining-oriented design rather than gaming optimization. The Geekbench OpenCL score of 21031 and Vulkan score of 19608 provide a more complete picture of raw compute throughput, with the OpenCL result being roughly 7% higher than the Vulkan score, suggesting that the architecture handles different API workloads with varying efficiency.
The deltaPct figures from the nearestRivals data show how tightly grouped this GPU is with its competition. The P106-090 trails the NVIDIA GeForce GTX 680 by 0.7%, and it matches that same 0.7% deficit against the AMD Radeon 660M. Against the NVIDIA RTX A2000 Mobile, the deficit is slightly larger at 0.8%. However, the P106-090 leads the NVIDIA GeForce GTX 570 by 1.1%. These margins are small enough that they fall within typical run-to-run variance for synthetic benchmarks, meaning the P106-090 is effectively performance-equivalent to the GTX 680 and Radeon 660M, while holding a slim but measurable advantage over the GTX 570.
Interpreting the FP32 throughput of 2.352 TFLOPS alongside the pixel rate of 73.49 GPixel/s and texture rate of 73.49 GTexel/s, the card shows a balanced compute-to-memory design. The 768 shading units, 48 TMUs, and 48 ROPs are configured in a manner that prioritizes consistent throughput over peak burst performance. The 1:64 ratio for FP16 (36.74 GFLOPS) indicates that half-precision workloads are severely de-emphasized, which is notable because many modern compute tasks leverage FP16 for acceleration; this card will not excel in those scenarios.
Ray Tracing and Feature Set
The P106-090 has no ray tracing cores and no tensor cores, as these are absent from the FACT PACK data. This means the card relies entirely on traditional rasterization and compute shaders for any rendering tasks. The API support includes DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4, which provides modern software compatibility, but without dedicated hardware acceleration for ray tracing, any such workloads will fall back to compute-based implementations that are substantially slower.
The lack of tensor cores also eliminates any AI-accelerated features such as DLSS or similar neural network-based upscaling. For a mining GPU, this omission is expected, as the card's purpose is raw shader and memory throughput rather than feature-rich graphics. The PCIe 1.0 x1 bus interface is a significant bottleneck for data transfer, though for mining workloads that primarily use local memory, this constraint is less impactful. The absence of display outputs confirms that this card cannot be used for any visual output, making it unsuitable for gaming or professional visualization without a secondary GPU.
The Vulkan 1.4 and OpenGL 4.6 support are current as of the data, but the lack of specialized cores means the feature set is essentially that of a mid-range Pascal card from 2016, with no forward-looking capabilities. The 16 nm process and 4,400 million transistors indicate a mature design that prioritizes power efficiency over raw performance.
How It Compares
NVIDIA GeForce GTX 680: The GTX 680 averages 13812 points, which is 0.7% higher than the P106-090's 13716. This places the two cards in a statistical tie, with the GTX 680 having a negligible edge. The GTX 680 is a desktop gaming card from an earlier generation, but its Kepler architecture delivers comparable compute results to the Pascal-based P106-090 in these benchmarks.
AMD Radeon 660M: This integrated graphics solution also scores 13812 points, matching the GTX 680 exactly and edging out the P106-090 by 0.7%. The Radeon 660M is a modern iGPU that benefits from newer architecture efficiency, yet the P106-090's dedicated 3 GB of GDDR5 memory and higher bandwidth do not translate into a measurable advantage in the aggregate benchmark score.
NVIDIA RTX A2000 Mobile: With an average score of 13821, the RTX A2000 Mobile is 0.8% ahead of the P106-090. This is the largest deficit among the rivals, though still within the margin of error. The RTX A2000 Mobile includes ray tracing and tensor cores, which do not appear to significantly impact these particular benchmark scores, as the differences are minimal.
NVIDIA GeForce GTX 570: The GTX 570 scores 13564, which is 1.1% lower than the P106-090. This is the only rival that the P106-090 definitively outperforms, though the margin is small. The GTX 570 is an older Fermi-based card, and the Pascal architecture's efficiency gains show in this modest lead, but the practical difference in real-world compute tasks would be negligible.
FAQ
Q: What is the average benchmark score for the P106-090?
A: The average benchmark score is 13716, which places it at the 54th percentile among all GPUs in the database.
Q: How does the P106-090 compare to the GeForce GTX 680?
A: The GTX 680 has an average score of 13812, which is 0.7% higher than the P106-090's 13716, making the two cards effectively equivalent in performance.
Q: Does the P106-090 support ray tracing?
A: No, the card has no ray tracing cores and no tensor cores, so ray tracing workloads would rely on slower compute-based methods, if supported at all.
Q: What is the memory configuration of the P106-090?
A: The card has 3 GB of GDDR5 memory on a 192-bit bus, providing 192.2 GB/s of bandwidth, with a memory clock of 2002 MHz (8 Gbps effective).
Q: Can the P106-090 output video to a display?
A: No, the card has no display outputs, meaning it cannot be connected to any monitor or used for visual output.
Q: What API versions are supported?
A: The card supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4, providing modern software compatibility despite its mining focus.
Power and Cooling
The P106-090 has a TDP of 75 W, which is a low power draw for a dual-slot card. The recommended power supply is 250 W, which is modest and suggests that the card can be paired with a wide range of systems, though the PCIe 1.0 x1 interface limits the host board requirements. The card requires a single 6-pin power connector, which is standard for this power class. The dual-slot design, at 250 mm in length (9.8 inches), indicates a full-size cooler that should handle the 75 W thermal load with relative ease.
The low TDP is a defining characteristic of this GPU, as it allows for simple cooling solutions and minimal impact on system power budgets. The 16 nm process node from TSMC contributes to this efficiency, and the 4,400 million transistors are packed into a die size of 200 mm², yielding a transistor density of 22.0M per mm². For a mining card running 24/7, the 75 W TDP is advantageous for reducing electricity costs over time, though the performance level is modest. The power connector requirement of one 6-pin is straightforward, and the 250 W PSU recommendation leaves ample headroom for the rest of the system.
Who Should Consider It
The P106-090 is a niche product that serves a specific purpose: compute workloads that do not require display output and that can tolerate a 3 GB memory capacity. Given its 54th percentile ranking and an average score of 13716, it is positioned in the lower-mid range of GPU performance. For users running mining operations that prioritize low power consumption per unit of compute, the 75 W TDP and 250 W PSU requirement make this an efficient option, though the 2.352 TFLOPS FP32 throughput is not competitive with modern cards.
At 1080p resolution, the card would struggle with demanding games due to the lack of display outputs, so it is not a gaming option at any settings. For compute tasks such as cryptocurrency mining, the 192.2 GB/s bandwidth and 48 ROPs provide adequate throughput for algorithms that favor memory bandwidth over FP16, given the 1:64 FP16 ratio. The absence of ray tracing and tensor cores makes it unsuitable for any AI or real-time ray tracing workloads, and the PCIe 1.0 x1 interface will bottleneck data transfer for tasks that require frequent host communication.
Users who have legacy compute jobs that fit within 3 GB of VRAM and require only OpenGL 4.6 or Vulkan 1.4 support may find the P106-090 acceptable, but the 0.7-0.8% deficit against the GTX 680 and Radeon 660M means there is no performance advantage over those alternatives. The 1.1% lead over the GTX 570 is the only competitive win, and even that is marginal. For anyone considering this card, the data suggests it is a low-power compute workhorse that is end-of-life, with no modern features and a performance profile that is roughly equivalent to a mid-range card from 2012-2013.
The AMD Equivalent of P106-090
Looking for a similar graphics card from AMD? The AMD Radeon RX Vega 64 offers comparable performance and features in the AMD lineup.
Popular NVIDIA P106-090 Comparisons
See how the P106-090 stacks up against similar graphics cards from the same generation and competing brands.
Compare P106-090 with Other GPUs
Select another GPU to compare specifications and benchmarks side-by-side.
Browse GPUs