SYSTEM ANALYZER

Rate My PC: AMD Ryzen 9 9950X + NVIDIA GeForce RTX 3090

Get a comprehensive performance analysis of your gaming rig with detailed benchmarks, bottleneck detection, and upgrade recommendations

95 / 100
ULTIMATE READY

Apex Performer

Top 5% of systems. Capable of 4K Ultra gaming and advanced rendering.

4K 60+ FPSVR ReadyRay Tracing

System Balance Analysis

CPU vs GPU performance ratio
Well Balanced
CPU
97%
VS
GPU
93%
PROCESSOR

AMD Ryzen 9 9950X

74,640 Benchmark Score
Top 3% Market Ranking
View Full Specs →
GRAPHICS CARD

NVIDIA GeForce RTX 3090

27,565 Benchmark Score
Top 7% Market Ranking
View Full Specs →

Market Position

How your build compares to others
Budget
0-30
Mid-Range
30-60
High-End
60-85
Enthusiast
85-100
Your Build

Game Performance Benchmarks

Real-world 4K FPS in popular titles
View All Games →

Performance Insights

Tips to maximize your system

Optimal Performance

Your system is in the top tier. You can run any modern game at maximum settings.

4K Gaming Ready

Consider a 4K 144Hz monitor to fully utilize your hardware capabilities.

Compatible Games See what you can play Compare CPUs Find upgrades Compare GPUs Find upgrades

Performance Tiers Explained

90-100

Ultimate

4K Ultra gaming, VR ready, ray tracing enabled, professional workloads

4K 60+ FPS VR Ready
70-89

High-End

1440p Ultra or 4K High settings, excellent for modern AAA titles

1440p Ultra 4K High
50-69

Mid-Range

1080p Ultra or 1440p Medium, great value for most gamers

1080p Ultra 1440p Med
30-49

Entry Level

1080p Medium settings, suitable for eSports and older titles

1080p Med eSports
0-29

Legacy

Basic gaming, older titles, consider upgrading for modern games

720p-1080p Low Older Games

CPU Analysis

The AMD Ryzen 9 9950X is the flagship 16-core processor in AMD's 9000 series, built on the Zen 5 architecture with the Granite Ridge codename. It is manufactured on TSMC's 4 nm process node, packing 16,630 million transistors across two 70.6 mm² dies. The chip operates with a base clock of 4.30 GHz and a boost clock of 5.70 GHz, with a TDP of 170 W. It supports DDR5 memory in a dual-channel configuration, offering a memory bandwidth of 89.6 GB/s, and includes ECC memory support.

The core layout is substantial: 16 cores and 32 threads. Each core carries 80 KB of L1 cache and 1 MB of L2 cache, while a shared 64 MB L3 pool provides ample capacity for demanding workloads. The CPU supports PCIe Gen 5 with 24 lanes from the CPU itself, and it includes integrated Radeon Graphics for basic display output. The multiplier is unlocked, making it a candidate for enthusiast overclocking.

Benchmark data reveals a processor that scales exceptionally well from lightly threaded to heavily threaded tasks. In 3DMark testing, the CPU scores 1,293 in single-thread, 2,543 in 2-thread, 4,958 in 4-thread, 9,298 in 8-thread, 16,263 in 16-thread, and 16,780 in max-thread tests. The scaling from 8 to 16 threads is nearly linear (9,298 to 16,263), indicating strong multi-core efficiency. From 16 to max threads, the gain is modest (16,263 to 16,780), suggesting the 16-core count is fully utilized and adding more logical threads yields diminishing returns.

In Cinebench, the results are equally telling. The R23 multi-core score is 40,924, while the single-core score is 2,202. That multi-core figure is roughly 18.6 times the single-core score, which is near the theoretical maximum for a 16-core/32-thread part with this architecture. Geekbench results show a single-core score of 3,029 and a multi-core score of 25,616, reinforcing the pattern of strong per-thread performance combined with excellent scaling.

PassMark tests break down specific workload characteristics. Integer math scores 242,097, floating-point math scores 159,063, and extended instructions (SIMD-heavy tasks) score 71,564. Data compression scores 896,544, while data encryption scores 44,366. Prime number finding scores 345, and random string sorting scores 94,368. The multi-thread score is 66,030, and the single-thread score is 4,737. Physics simulation scores 3,279. These numbers indicate a CPU that is particularly strong in integer-heavy and compression tasks, which are common in database work, scientific computing, and content creation pipelines.

The processor's percentile rank versus all CPUs is 94, placing it in the top 6% of all processors tracked. Its average benchmark score is 74,640. Compared to its nearest rivals, the Ryzen 9 9950X is effectively tied with the AMD Ryzen 7 PRO 9745 (deltaPct -0.2, meaning the 9950X is 0.2% behind), the AMD Ryzen AI 9 HX PRO 475 (deltaPct 0.2, meaning the 9950X is 0.2% ahead), the AMD EPYC 4545P (deltaPct -1, meaning the 9950X is 1% behind), and the Intel Core Ultra 9 285 (deltaPct -1.1, meaning the 9950X is 1.1% behind). These are extremely tight margins, indicating that the 9950X sits at the very top of the performance hierarchy, trading blows with the best server and mobile parts available.

Benchmark Performance

The CPU's aggregate benchmark profile is exceptional. With an average benchmark score of 74,640 and a 94th percentile ranking among all CPUs, it sits in the top tier. The GPU, an NVIDIA GeForce RTX 3090, posts an average benchmark score of 27,565 and ranks in the 73rd percentile among all GPUs.

The RTX 3090's individual benchmark results are as follows: 3DMark Steel Nomad DX12 scores 5,118; Geekbench OpenCL scores 172,758; Geekbench Vulkan scores 53,927. PassMark tests show DirectX 9 at 268, DirectX 10 at 182, DirectX 11 at 220, DirectX 12 at 110, G2D at 1,063, G3D at 26,645, and GPU compute at 15,356. The G3D score of 26,645 is the primary gaming metric, while the GPU compute score of 15,356 reflects compute workloads.

The GPU's nearest rivals provide context. The NVIDIA GeForce RTX 4070 Mobile scores an average of 27,435, which is 0.5% behind the RTX 3090. The AMD Radeon RX 6700 XT scores 27,425, also 0.5% behind. The AMD Radeon Pro Vega 20 scores 27,839, putting the RTX 3090 1% behind it. The AMD Radeon RX 7800M scores 27,883, placing the RTX 3090 1.1% behind. These margins are small, meaning the RTX 3090 is competitive with a range of modern mid-range and high-end GPUs, though it is no longer at the current-generation.

The combined percentile for this CPU+GPU pairing is 84. This means the system outperforms 84% of all tracked desktop combinations. The CPU is the clear standout component, with its 94th percentile ranking far exceeding the GPU's 73rd percentile. This disparity suggests the CPU has significantly more headroom than the GPU in most tasks.

There are no measured FPS rows for this exact combination in the data. The FACT PACK contains no measuredFps data for the Ryzen 9 9950X + RTX 3090 pairing. Consequently, all frame rate discussions below are estimates derived from the benchmark scores, not direct measurements.

Gaming Performance

No measured FPS data exists for this specific CPU+GPU combination. The FACT PACK contains no measuredFpsUltraByGame entries, so all frame rate figures in this section are estimates based on the benchmark scores of the CPU and GPU, rather than empirical testing of the pairing.

The RTX 3090's PassMark G3D score of 26,645 and 3DMark Steel Nomad DX12 score of 5,118 indicate a GPU capable of high refresh rate gaming at 1440p and solid performance at 4K. The GPU's 73rd percentile ranking places it above the majority of discrete GPUs. Its nearest rivals, the RTX 4070 Mobile and RX 6700 XT, are both within 0.5% of its average score, suggesting the RTX 3090 will deliver frame rates comparable to those cards in most titles.

The CPU's gaming-relevant benchmarks are strong. The 3DMark single-thread score of 1,293 and the PassMark single-thread score of 4,737 indicate excellent per-core performance, which is critical for games that rely on a few fast threads. The 8-thread 3DMark score of 9,298 shows that even moderately threaded games will have ample CPU headroom. For a 16-core processor, the gaming bottleneck will almost never be the CPU; instead, the GPU will be the limiting factor at high resolutions.

At 1080p, the combination of a top-tier CPU and a 73rd percentile GPU suggests frame rates will be very high, likely well above 100 FPS in most esports and competitive titles, and comfortably above 60 FPS in demanding AAA games. The CPU's single-thread performance will ensure that even poorly optimized games that depend on a single core will run smoothly. At 1440p, the GPU will become more of a factor, but the RTX 3090's large memory bandwidth (936.2 GB/s) and 24 GB GDDR6X memory will help maintain high frame rates in memory-intensive scenes. At 4K, the GPU will be the primary bottleneck, and the frame rates will depend heavily on the specific game and settings.

It is important to reiterate that these are estimated figures. The data does not provide measured frame rates for this pairing, so the actual gaming performance could vary based on drivers, game optimizations, and system configuration.

Upgrade Path and Platform

The Ryzen 9 9950X uses the AMD Socket AM5 platform. This socket is the foundation for AMD's current-generation desktop processors, and it supports DDR5 memory exclusively. The CPU's dual-channel memory controller provides 89.6 GB/s of bandwidth, which is sufficient for the 16-core processor's demands.

The platform supports PCIe Gen 5 with 24 lanes from the CPU, which provides ample bandwidth for the fastest NVMe SSDs and expansion cards. The RTX 3090, however, uses a PCIe 4.0 x16 interface. This means the GPU will run at PCIe 4.0 speeds on an AM5 board, which is backward compatible and will not be a bottleneck in most scenarios. The GPU's power requirements include a TDP of 350 W, with a suggested PSU of 750 W. The CPU's TDP is 170 W, bringing the combined power draw of the two primary components to 520 W, leaving roughly 230 W of headroom in a 750 W PSU for the rest of the system.

The RTX 3090 is an end-of-life product, with its release date of 2020-08-31 and its successor being the GeForce 40 series. Its predecessor was the GeForce 20 series. This means the GPU is two generations old as of the CPU's release in 2024-08-14. For a user looking to upgrade, the platform itself (AM5) is current and will support future AMD processors. The most sensible next upgrade for this system would be a newer-generation GPU, given that the CPU has significantly more performance headroom than the GPU. The CPU's 94th percentile ranking versus the GPU's 73rd percentile suggests that the GPU is the limiting factor in gaming and GPU-accelerated compute tasks.

The motherboard should be chosen with care, as the PCIe Gen 5 lanes from the CPU require a compatible board to take full advantage of the fastest storage. The RTX 3090's triple-slot width and 336 mm length require a case with sufficient clearance. The power connector is a single 12-pin, which may require an adapter for standard PSUs.

FAQ

Q: What is the core and thread count of the AMD Ryzen 9 9950X?

A: The Ryzen 9 9950X has 16 cores and 32 threads, based on the Zen 5 architecture.

Q: How does the CPU compare to its nearest rival, the AMD Ryzen 7 PRO 9745?

A: The Ryzen 9 9950X has an average benchmark score of 74,640, which is 0.2% lower than the Ryzen 7 PRO 9745's average score of 74,761.

Q: What is the memory bandwidth of the RTX 3090?

A: The RTX 3090 has a memory bandwidth of 936.2 GB/s, using a 384-bit bus with GDDR6X memory.

Q: Is the RTX 3090 still in production?

A: No, the RTX 3090 is end-of-life, with a release date of 2020-08-31 and a successor in the GeForce 40 series.

Q: What is the suggested PSU wattage for a system with the RTX 3090?

A: The suggested PSU for the RTX 3090 is 750 W, given the GPU's 350 W TDP.

Q: What is the CPU's socket type and memory support?

A: The Ryzen 9 9950X uses the AMD Socket AM5 and supports DDR5 memory in a dual-channel configuration.

Q: How does the CPU's single-thread performance compare to its multi-thread performance?

A: The CPU's 3DMark single-thread score is 1,293, while its max-thread score is 16,780, showing strong scaling across cores.

Who Should Build It

This system targets users who need exceptional CPU performance with solid, but not top-tier, GPU capability. The CPU's 94th percentile ranking and the GPU's 73rd percentile ranking create a profile suited to specific types of workloads.

Content creators working with video editing, 3D rendering, and large data processing will benefit most. The Cinebench R23 multi-core score of 40,924 and the PassMark multi-thread score of 66,030 indicate a CPU that can handle heavily threaded workloads with ease. The data compression score of 896,544 and encryption score of 44,366 suggest strong performance in file archiving and security-related tasks.

Developers compiling large codebases will appreciate the 16 cores and 32 threads, as well as the high single-thread performance (Geekbench single-core score of 3,029) for faster build times. The CPU's floating-point math score of 159,063 and extended instructions score of 71,564 are relevant for scientific computing and simulation workloads.

Gamers at 1440p and 4K resolutions will find the RTX 3090 capable, though it is no longer at the top of the GPU hierarchy. The GPU's 24 GB of VRAM is substantial, which is useful for high-resolution textures and modding. However, gamers seeking the absolute highest frame rates at 4K might find the GPU's 73rd percentile ranking limiting.

Students and professionals working with large datasets, such as financial modeling or data analysis, will benefit from the CPU's integer math score of 242,097 and its strong multi-threaded performance. Small business workstations running virtualization or database workloads will also find the 16-core configuration advantageous.

The system is less suited for users who prioritize gaming over compute, as the GPU is the weaker component. For those users, a more balanced build with a lower-tier CPU and a higher-tier GPU would be more appropriate.

GPU Analysis

The NVIDIA GeForce RTX 3090 is built on the Ampere architecture, using the GA102 chip. It is manufactured on Samsung's 8 nm process node, with 28,300 million transistors on a 628 mm² die. The GPU has a base clock of 1395 MHz and a boost clock of 1695 MHz. Memory runs at 1219 MHz, translating to 19.5 Gbps effective.

The memory subsystem is a defining feature. The RTX 3090 has 24 GB of GDDR6X memory on a 384-bit bus, yielding a bandwidth of 936.2 GB/s. This is a massive amount of VRAM, suitable for high-resolution textures, large 3D scenes, and machine learning models that require substantial memory capacity.

The compute configuration includes 10,496 shading units, 328 texture mapping units, and 112 raster operation units. Ray tracing is handled by 82 RT cores, while 328 tensor cores accelerate AI and DLSS workloads. The pixel rate is 189.8 GPixel/s, and the texture rate is 556.0 GTexel/s. The FP32 performance is 35.58 TFLOPS, with FP16 also at 35.58 TFLOPS (1:1 ratio).

Benchmark results show the GPU's capabilities. The 3DMark Steel Nomad DX12 score of 5,118 is a modern DirectX 12 test that reflects current gaming workloads. The Geekbench OpenCL score of 172,758 and Vulkan score of 53,927 indicate strong compute performance. PassMark G3D score of 26,645 and GPU compute score of 15,356 round out the picture.

The GPU's 73rd percentile ranking among all GPUs is respectable but not elite. Its nearest rivals are all within 1.1% of its average score, meaning the RTX 3090 is firmly in the upper-midrange tier of GPUs as of the data collection period. The 24 GB VRAM is unusual for this tier, however, making it attractive for specific workloads like large language model inference or high-resolution rendering where memory capacity is more important than raw throughput.

The GPU's power requirements are substantial. With a TDP of 350 W and a suggested PSU of 750 W, it draws significantly more power than the CPU. The triple-slot width and 336 mm length require a large case with good airflow. The power is delivered via a single 12-pin connector.

Build Overview

This is a desktop build combining the AMD Ryzen 9 9950X CPU with the NVIDIA GeForce RTX 3090 GPU. The pairing represents a high-end CPU from 2024 with a high-end GPU from 2020, creating an interesting performance asymmetry.

The combined percentile for this system is 84, meaning it outperforms 84% of all tracked desktop configurations. The CPU is the dominant component, ranked in the 94th percentile among all CPUs, while the GPU is ranked in the 73rd percentile among all GPUs. This is a significant gap of 21 percentile points, indicating that the CPU is substantially more powerful relative to its peers than the GPU is relative to its peers.

The system's overall tier is high, driven primarily by the CPU's exceptional performance. The RTX 3090, while no longer a top-tier GPU, is still a capable card that can handle demanding games and compute workloads, especially given its large 24 GB memory buffer. The combination is best described as a workstation-class CPU paired with a strong, but aging, high-end GPU.

The CPU's launch MSRP was $649. The GPU's launch MSRP was 1,499 USD. These figures represent the initial pricing, not current market values.

For users who already own this system, the CPU offers significant future-proofing. The AM5 platform and DDR5 memory support will allow for GPU upgrades without changing the motherboard or memory. The RTX 3090, being end-of-life, is the component most likely to be replaced first, especially for users seeking higher frame rates at 4K or improved ray tracing performance.

Balance and Bottleneck

The performance asymmetry between the CPU and GPU is the defining characteristic of this build. The CPU ranks in the 94th percentile, while the GPU ranks in the 73rd percentile. This 21-point gap means the CPU is capable of far more work than the GPU can feed or process in most scenarios.

In CPU-bound workloads, such as video encoding, 3D rendering, data compression, and scientific simulations, the CPU will be the primary workhorse. The Cinebench R23 multi-core score of 40,924 and Geekbench multi-core score of 25,616 show a processor that can sustain heavy multi-threaded loads. In these tasks, the GPU will be underutilized, and the system will perform at a level consistent with the CPU's 94th percentile ranking.

In GPU-bound workloads, such as gaming at high resolutions or GPU-accelerated rendering, the GPU will be the limiting factor. The RTX 3090's 73rd percentile ranking means it will deliver performance consistent with that tier, leaving the CPU with significant headroom. At 1080p gaming, the CPU may not be fully utilized, but at 4K, the GPU will be the clear bottleneck.

The FPS scaling evidence, while estimated, supports this analysis. Since there is no measured FPS data for this pairing, the balance assessment relies on the benchmark scores. The CPU's 3DMark 8-thread score of 9,298 is more than sufficient for modern games, which typically use fewer than 8 threads. The GPU's PassMark G3D score of 26,645 is the more likely constraint in gaming.

For mixed workloads, such as game streaming or recording while playing, the CPU's 16 cores provide ample overhead. The CPU can handle encoding tasks while the GPU focuses on rendering, resulting in a system that is well-balanced for content creation and multitasking, even if the GPU is the weaker link in pure gaming scenarios.

The RTX 3090's 24 GB VRAM is another factor in the balance equation. While the GPU's compute throughput is in the 73rd percentile, its memory capacity is exceptional, allowing it to handle datasets and textures that would exceed the capacity of many newer, faster GPUs. This makes the system well-suited for machine learning inference and large-scale 3D rendering, where the GPU's memory capacity can partially compensate for its lower raw performance.