SYSTEM ANALYZER

Rate My PC: AMD Ryzen 9 9900X + NVIDIA GeForce RTX 3090

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

94 / 100
ULTIMATE READY

Apex Performer

Top 6% 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
95%
VS
GPU
93%
PROCESSOR

AMD Ryzen 9 9900X

57,498 Benchmark Score
Top 5% 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

# AMD Ryzen 9 9900X + NVIDIA GeForce RTX 3090: Desktop Performance Analysis

This pairing combines AMD's 12-core Zen 5 flagship, the Ryzen 9 9900X, with NVIDIA's Ampere-based RTX 3090, a 24 GB GDDR6X graphics card. The CPU sits in the 92nd percentile among all processors, while the GPU holds the 73rd percentile among all graphics cards, placing the combined build in the 83rd percentile overall. No measured FPS data exists for this exact combination, so all gaming frame-rate discussion is estimated from the individual component benchmark scores.

Usage Scenarios

For high-refresh gaming, this system is capable but not evenly matched. The RTX 3090's PassMark G3D score of 26645 places it near the RTX 4070 Mobile (deltaPct 0.5) and RX 6700 XT (deltaPct 0.5) in raw graphics compute, which suggests it can drive high frame rates at lower resolutions where the CPU's single-thread performance of 3010 in Geekbench and 1286 in 3DMark single-thread become relevant. At 1080p or 1440p, the Ryzen 9 9900X's strong single-core showing (92nd percentile overall) should keep frame pacing consistent, though the GPU's 73rd percentile position means 4K high-refresh gaming will likely stress the graphics card first.

Streaming and content creation benefit from the CPU's 12 cores and 24 threads. The Cinebench R23 multi-core score of 32172 and Geekbench multi-core score of 22174 indicate heavy multi-threaded lifting for video encoding, while the RTX 3090's 328 tensor cores and 82 RT cores offload AI-enhanced encoding and real-time effects. The 24 GB VRAM buffer at 936.2 GB/s bandwidth is ample for holding multiple video streams or large preview buffers during broadcast work, but the GPU's overall percentile suggests it will be the limiting factor in simultaneous encode and render workloads.

Video editing software that leverages both CPU and GPU acceleration will see the Ryzen 9 9900X excel in timeline scrubbing and export encoding, with its PassMark multi-thread score of 54643 and data compression score of 683579. The RTX 3090's DirectX 12 score of 110 in PassMark and 3DMark Steel Nomad DX12 score of 5118 indicate solid GPU-accelerated effects rendering, though the graphics card trails newer architectures in raw throughput. For 4K multi-track timelines, the 24 GB VRAM prevents out-of-memory stalls, but the GPU's 73rd percentile ranking means effects-heavy projects may bottleneck on the graphics card.

3D rendering and CAD workloads are a strong suit for this CPU-GPU combo. The Ryzen 9 9900X's Cinebench R15 multi-core score of 5008 and PassMark floating-point math score of 120083 show excellent CPU ray-tracing geometry preparation, while the RTX 3090's FP32 compute of 35.58 TFLOPS and 35.58 TFLOPS FP16 (1:1) handle GPU-accelerated renders. The 82 RT cores provide dedicated hardware for real-time ray tracing, and the 328 texture mapping units deliver a texture rate of 556.0 GTexel/s. However, the GPU's 73rd percentile position means it will lag behind higher-tier cards in final-frame renders, making the CPU the stronger half of this pairing for non-GPU-accelerated render engines.

Software development benefits from the CPU's 12 cores in compilation tasks, with PassMark integer math scoring 181056 and extended instructions at 55243. The 64 MB L3 cache and 89.6 GB/s memory bandwidth reduce cache misses during large codebase builds, while the RTX 3090's 24 GB VRAM supports local LLM inference and GPU-accelerated testing. The dual-channel DDR5 memory support and ECC capability add reliability for long-running build servers. The CPU's 3DMark 16-thread score of 12552 indicates strong parallel compilation throughput, though the GPU's compute score of 15356 in PassMark shows it can accelerate certain test suites.

For student and office work, this build is massively overprovisioned. The CPU's PassMark single-thread score of 4672 and 3DMark 2-thread score of 2519 handle document processing and spreadsheet calculations with ease, while the integrated Radeon Graphics provide a fallback display output. The RTX 3090's triple-slot design and 350 W TDP make it a poor fit for small desks or quiet environments, and the 336 mm length requires a full tower case. The 92nd percentile CPU ranking means even intensive data analysis in Python or R will feel instant, but the GPU's 73rd percentile is wasted on typical office applications that use only basic 2D acceleration.

Benchmark Performance

The Ryzen 9 9900X achieves an average benchmark score of 57498, placing it in the 92nd percentile of all CPUs. Its nearest rivals include the AMD EPYC 9015 (deltaPct -0.1), AMD EPYC 7313 (deltaPct 0.2), Intel Core i9-14900 (deltaPct -1.1), and Intel Xeon Platinum 8260M (deltaPct -1.4). This places the 9900X effectively at parity with dual-socket server parts and slightly ahead of the Core i9-14900 in aggregate performance, despite the Intel chip's higher boost potential.

The NVIDIA RTX 3090 averages 27565 across its benchmark suite, holding the 73rd percentile among all GPUs. Its nearest rivals are the RTX 4070 Mobile (deltaPct 0.5), RX 6700 XT (deltaPct 0.5), Radeon Pro Vega 20 (deltaPct -1), and RX 7800M (deltaPct -1.1). The GPU's position is notably lower than the CPU's, indicating this is a processor-heavy build where the graphics card is roughly average for a modern desktop, not a flagship performer.

The combined percentile of 83 reflects this imbalance. The CPU's 92nd percentile score dominates the aggregate, while the GPU's 73rd percentile drags the overall figure down. In CPU-bound benchmarks like Cinebench R23 multi-core (32172) and Geekbench multi-core (22174), the 9900X outperforms its rival EPYC 9015 by 0.1% despite the EPYC being a server-class part, demonstrating the desktop chip's strong multi-thread scaling. The GPU's PassMark G3D score of 26645 is within 0.5% of the RTX 4070 Mobile, showing that the 3090's desktop advantage over mobile parts is minimal in raw compute.

Single-thread performance is a clear strength: the CPU's 3DMark single-thread score of 1286 and Cinebench R15 single-core score of 353 are exceptional for a 12-core part. The GPU's DirectX 9 score of 268 and DirectX 10 score of 182 in PassMark reflect its legacy API efficiency, while the DirectX 12 score of 110 and Steel Nomad DX12 score of 5118 show modern API scaling is less impressive relative to its peak.

Balance and Bottleneck

The data indicates a CPU-heavy imbalance. The Ryzen 9 9900X's 92nd percentile dwarfs the RTX 3090's 73rd percentile, meaning in CPU-bound workloads like data compression (PassMark 683579) or prime number finding (436), the processor will finish tasks long before the GPU is utilized. Conversely, in GPU-bound scenarios like 4K gaming or GPU rendering, the 3090's average performance relative to other GPUs will cap frame rates regardless of the CPU's headroom.

FPS scaling in games would show this bottleneck pattern. At lower resolutions where CPU throughput matters more, the 9900X's 3DMark 8-thread score of 9114 and 16-thread score of 12552 would allow high frame rates, but the RTX 3090's 73rd percentile G3D score means the graphics card becomes the constraint as resolution and detail settings increase. The lack of measured FPS data for this combination prevents exact quantification, but the percentile gap of 19 points between CPU and GPU suggests the processor will frequently wait on the graphics card in gaming workloads.

Compute-heavy applications show a similar split. The CPU's PassMark multi-thread score of 54643 and floating-point math score of 120083 indicate that CPU-bound scientific computing will saturate all 12 cores, while the GPU's compute score of 15356 in PassMark is modest for a 24 GB card. This suggests the 3090 is not the bottleneck in CUDA-optimized workloads but will lag behind higher-percentile GPUs in raw parallel throughput. The 89.6 GB/s CPU memory bandwidth versus the GPU's 936.2 GB/s bandwidth highlights that data transfers between CPU and GPU could become a limiting factor in mixed workloads.

The 120 W TDP of the CPU versus the 350 W TDP of the GPU creates a power balance where the graphics card dominates system draw. A 750 W suggested PSU provides adequate headroom for both components under load, but overclocking the CPU (multiplier unlocked) or GPU would require careful power budgeting. The CPU's dual-channel memory bus at 89.6 GB/s is a potential bottleneck for memory-intensive workloads, as the GPU's 384-bit bus at 936.2 GB/s moves data far faster.

Who Should Build It

Gamers targeting 1440p or 1080p high-refresh displays will find this build adequate, but not for 4K ultra settings. The CPU's 92nd percentile single-thread performance (Geekbench single-core 3010) ensures high frame rates in CPU-bound titles, while the RTX 3090's 73rd percentile G3D score (26645) means it can handle 1440p ultra at playable rates. At 4K, the GPU's average standing will require reduced settings to maintain 60 FPS, making this a better 1440p high-refresh machine.

Content creators working with 4K video or large 3D scenes benefit from the CPU's 12 cores and the GPU's 24 GB VRAM. The Cinebench R23 multi-core score of 32172 accelerates rendering, while the 24 GB frame buffer at 936.2 GB/s handles textures and previews without swapping. The GPU's 82 RT cores support real-time ray tracing in rendering software, but its 73rd percentile means final renders will be slower than with higher-tier GPUs.

Software developers compiling large codebases will appreciate the CPU's PassMark integer math score of 181056 and extended instructions score of 55243. The 64 MB L3 cache reduces rebuild times, and the 24 threads handle parallel test suites efficiently. The GPU's 24 GB VRAM is useful for running local machine learning models, though its compute score of 15356 in PassMark is modest for that purpose.

Students and small business users building a workstation should consider this overkill. The CPU's 92nd percentile handles any academic or office workload, but the GPU's 350 W TDP and triple-slot size add unnecessary heat and power draw for document processing. The integrated Radeon Graphics in the CPU could handle basic display tasks, making the RTX 3090 optional for non-graphics workloads. The combined 83rd percentile suggests this is a specialized tool, not a general-purpose office machine.

CPU Analysis

The AMD Ryzen 9 9900X is a 12-core, 24-thread processor based on the Zen 5 architecture, codenamed Granite Ridge, fabricated on TSMC's 4 nm process. It contains 16,630 million transistors across a 2x 70.6 mm² die, with a base clock of 4.40 GHz and boost clock of 5.60 GHz. The 120 W TDP and unlocked multiplier allow aggressive overclocking on AMD Socket AM5 platforms.

The cache hierarchy features 80 KB L1 per core, 1 MB L2 per core, and 64 MB shared L3, providing substantial on-die storage for frequently accessed data. Memory support is DDR5 with dual-channel configuration, delivering 89.6 GB/s bandwidth and ECC capability for error correction in critical workloads. PCIe Gen 5 with 24 lanes (CPU only) provides high-bandwidth connectivity for GPUs and NVMe storage.

Benchmark results show exceptional multi-thread scaling. The 3DMark max-threads score of 13929 is only 11% higher than the 16-thread score of 12552, indicating diminishing returns beyond 16 threads in that test. The Cinebench R23 multi-core score of 32172 and Geekbench multi-core score of 22174 place it above the EPYC 7313 (deltaPct 0.2) and near the EPYC 9015 (deltaPct -0.1), showing server-level throughput in a desktop package.

Single-core performance is equally impressive. The Geekbench single-core score of 3010 and 3DMark single-thread score of 1286 demonstrate strong IPC improvements from Zen 5. The PassMark single-thread score of 4672 and Cinebench R23 single-core score of 2253 confirm that the 9900X excels in lightly-threaded workloads, making it suitable for gaming and legacy applications that rely on single-thread performance.

The 92nd percentile ranking reflects this dual strength. In real workloads, the 9900X's PassMark data compression score of 683579 and floating-point math score of 120083 indicate rapid data processing, while the find prime numbers score of 436 and random string sorting score of 72013 show consistent performance across diverse task types. The CPU's release date of 2024-08-14 with a launch MSRP of $499 positions it as a premium desktop part.

GPU Analysis

The NVIDIA GeForce RTX 3090 is built on the GA102 chip using Samsung's 8 nm process, with 28,300 million transistors on a 628 mm² die. It features 10496 shading units, 328 texture mapping units, 112 ROPs, 82 RT cores, and 328 tensor cores. The base clock is 1395 MHz with a boost clock of 1695 MHz, and memory runs at 1219 MHz (19.5 Gbps effective).

Memory configuration is substantial: 24 GB of GDDR6X on a 384-bit bus delivers 936.2 GB/s bandwidth. This is the card's defining feature, enabling large texture sets, massive compute buffers, and AI model loading without VRAM constraints. The pixel rate of 189.8 GPixel/s and texture rate of 556.0 GTexel/s support high-resolution rendering, while FP32 and FP16 both at 35.58 TFLOPS (1:1) provide balanced compute.

Benchmark scores reveal a mid-tier position. The PassMark G3D score of 26645 places it at 73rd percentile, with the RTX 4070 Mobile (deltaPct 0.5) and RX 6700 XT (deltaPct 0.5) as nearest rivals. The 3DMark Steel Nomad DX12 score of 5118 and Geekbench Vulkan score of 53927 show modern API performance, while the Geekbench OpenCL score of 172758 indicates strong compute capability.

The 73rd percentile ranking is telling for a card with 24 GB VRAM and 82 RT cores. In raw rasterization, it barely edges out the RX 6700 XT by 0.5%, suggesting that the large memory and tensor cores do not translate to higher frame rates in traditional games. The DirectX 12 score of 110 in PassMark is surprisingly low, indicating potential driver or API overhead issues. The card's end-of-life production status and successor in the GeForce 40 series further contextualize its mid-tier standing.

For rendering workloads, the 24 GB VRAM is the primary advantage. The 936.2 GB/s bandwidth supports high-resolution textures and complex scenes, while the 328 tensor cores accelerate AI denoising and DLSS. The 82 RT cores provide hardware ray tracing, but the 73rd percentile suggests that ray-traced performance is not class-leading. The triple-slot design and 350 W TDP require robust cooling and a 750 W suggested PSU.

Upgrade Path and Platform

The AMD Socket AM5 platform provides a clear upgrade path. The Ryzen 9 9900X supports DDR5 memory with dual-channel configuration and 89.6 GB/s bandwidth, with ECC capability for workstations. PCIe Gen 5 with 24 lanes (CPU only) accommodates current GPUs and NVMe drives, with headroom for future PCIe 5.0 peripherals. The 120 W TDP of the CPU leaves thermal and power headroom for higher-core-count Ryzen 9 parts in the same socket.

The RTX 3090 uses PCIe 4.0 x16, which is backward-compatible with the CPU's PCIe Gen 5 lanes. The GPU's 350 W TDP and triple-slot size require a case with sufficient clearance (336 mm length) and power delivery. The 750 W suggested PSU provides adequate headroom for the CPU (120 W) and GPU (350 W) under load, but a higher-wattage PSU would be advisable for overclocking both components.

A sensible next upgrade would be to the GPU, given the CPU's 92nd percentile standing. The RTX 3090's 73rd percentile is the system's weakest link, so replacing it with a higher-percentile GPU would balance the build without changing the platform. Alternatively, adding a PCIe Gen 5 NVMe drive would leverage the CPU's 24 lanes for faster storage, though the dual-channel memory bus at 89.6 GB/s remains a potential bottleneck. The CPU's unlocked multiplier allows overclocking to extend its lifespan, but the 120 W TDP limits headroom without enhanced cooling.

For memory upgrades, the dual-channel DDR5 configuration supports higher-capacity kits, and ECC support is valuable for error-sensitive workloads. The 64 MB L3 cache reduces memory pressure, but the 89.6 GB/s bandwidth is modest compared to the GPU's 936.2 GB/s, so memory-bound tasks may see limited gains from faster RAM. The platform's 4 nm process and TSMC foundry ensure efficient power delivery for sustained workloads.

FAQ

Q: What is the combined percentile ranking of this CPU-GPU pair?

A: The combined percentile is 83, reflecting the CPU's 92nd percentile and the GPU's 73rd percentile.

Q: How does the Ryzen 9 9900X compare to the Intel Core i9-14900 in benchmark scores?

A: The 9900X has an average benchmark score of 57498, which is 1.1% higher than the Core i9-14900's score of 58115 (deltaPct -1.1).

Q: What is the RTX 3090's nearest rival in benchmark performance?

A: The RTX 3090's score of 27565 is within 0.5% of both the RTX 4070 Mobile (27435) and RX 6700 XT (27425).

Q: How much VRAM does the RTX 3090 have and what is its bandwidth?

A: It has 24 GB of GDDR6X memory on a 384-bit bus, delivering 936.2 GB/s bandwidth.

Q: What is the CPU's boost clock and TDP?

A: The boost clock is 5.60 GHz with a base clock of 4.40 GHz, and the TDP is 120 W.

Q: Does the CPU support ECC memory?

A: Yes, the Ryzen 9 9900X supports ECC memory with its dual-channel DDR5 configuration.

Q: What is the GPU's production status?

A: The RTX 3090 is end-of-life, with the GeForce 40 series as its successor.

Gaming Performance

No measured FPS data exists for this exact CPU-GPU combination, so all frame rate figures are estimates based on the benchmark scores. The RTX 3090's 73rd percentile G3D score of 26645 suggests it performs around the level of the RX 6700 XT (deltaPct 0.5) in rasterized games, meaning 1080p and 1440p ultra settings should achieve high frame rates in most titles. The CPU's 92nd percentile single-thread performance (Geekbench single-core 3010) ensures that CPU-bound games will not be bottlenecked.

At 1080p ultra, the CPU's strong single-core and 8-thread scores (9114 in 3DMark) would allow frame rates to push toward the GPU's maximum output, but the GPU's average standing means 1440p is the realistic sweet spot. At 1440p ultra, the 3090's 24 GB VRAM and 936.2 GB/s bandwidth handle texture-heavy scenes, while the 82 RT cores provide ray tracing capability, though at lower frame rates than newer GPUs. At 4K ultra, the GPU's 73rd percentile would struggle to maintain 60 FPS in demanding titles, requiring reduced settings or DLSS.

The DirectX 12 score of 110 in PassMark and Steel Nomad DX12 score of 5118 indicate that modern API games will perform adequately but not exceptionally. The GPU's Vulkan score of 53927 in Geekbench suggests better scaling in Vulkan-based titles. The 350 W TDP and triple-slot design generate significant heat, so sustained gaming sessions may see thermal throttling in poorly ventilated cases. The 750 W suggested PSU provides sufficient power for the CPU and GPU under gaming loads.

Build Overview

This is a desktop-class build combining the AMD Ryzen 9 9900X with the NVIDIA GeForce RTX 3090. The CPU is a 12-core Zen 5 part on AMD Socket AM5, released in August 2024 with a launch MSRP of $499, while the GPU is an Ampere-based card from August 2020 with a launch MSRP of 1,499 USD. The CPU is in active production, whereas the GPU is end-of-life.

The combined 83rd percentile places this build in the upper tier of desktop systems, but the imbalance is notable: the CPU at 92nd percentile is a top-tier processor, while the GPU at 73rd percentile is merely above average. The CPU's average benchmark score of 57498 rivals server-class EPYC parts, while the GPU's 27565 average is comparable to mid-range mobile and desktop GPUs. This creates a system that excels in CPU-intensive workloads like compilation, data processing, and multi-threaded rendering, but is only average in GPU-bound tasks like high-resolution gaming and GPU-accelerated rendering.

The 24 GB VRAM on the RTX 3090 is its primary differentiator, providing capacity that exceeds its raw compute ranking. The CPU's 64 MB L3 cache and 89.6 GB/s memory bandwidth complement this for data-heavy workloads. The build class is desktop, and the overall tier is high-end CPU with mid-high GPU, making it a specialized workstation rather than a balanced gaming rig. The lack of measured FPS data means gaming performance is estimated, but the percentile gap suggests users should prioritize CPU-bound productivity tasks over GPU-bound gaming.