SYSTEM ANALYZER

Rate My PC: Intel Core i9-12900KS + NVIDIA GeForce RTX 3090

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

93 / 100
ULTIMATE READY

Apex Performer

Top 7% 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
93%
VS
GPU
93%
PROCESSOR

Intel Core i9-12900KS

45,094 Benchmark Score
Top 7% 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

# Balance and Bottleneck

The Intel Core i9-12900KS and NVIDIA GeForce RTX 3090 pairing presents an intriguing balance question, as the data reveals a CPU that sits in the 89th percentile among all processors and a GPU in the 73rd percentile among all graphics cards. This percentile gap suggests the CPU is the stronger component relative to its peers, but the bottleneck picture is more nuanced than a simple percentile comparison.

The CPU's benchmark scores show exceptional scaling from 2 threads to 16 threads. The 3DMark 2-thread score of 2212 climbs to 4320 at 4 threads, then 7872 at 8 threads, and reaches 10316 at 16 threads, with a max-thread score of 11897. This scaling curve is nearly linear through 8 threads, indicating the hybrid Alder Lake architecture handles thread addition efficiently. However, the jump from 16 threads to max threads (24 threads total) yields only a 15% improvement, suggesting diminishing returns beyond 16 threads — a sign that the 8 Efficiency cores contribute meaningfully but not proportionally to performance.

The RTX 3090, with its 82 RT cores and 328 tensor cores, presents a different bottleneck profile. The GPU's passmark_g3d score of 26645 and 3DMark Steel Nomad DX12 score of 5118 place it in a competitive tier, but its nearest rivals include the RTX 4070 Mobile (0.5% ahead), RX 6700 XT (0.5% ahead), Radeon Pro Vega 20 (1% behind), and RX 7800M (1.1% behind). This clustering suggests the GPU is not a runaway leader in raw compute, and in gaming workloads, the CPU's strong single-thread performance (3DMark single-thread score of 1121, Cinebench R23 single-core of 5203) will likely keep pace with the GPU's demands.

The memory bandwidth situation deserves attention. The CPU supports dual-channel DDR4 and DDR5 with a memory bandwidth of 76.8 GB/s, while the GPU has 936.2 GB/s of bandwidth on its 384-bit GDDR6X interface. This 12x disparity means the GPU handles its own memory traffic independently, but the CPU's memory bandwidth could become a limiting factor in scenarios requiring frequent data transfers between CPU and GPU, such as physics simulations or large asset streaming.

For gaming at 1080p, the CPU's strong single-thread performance (Passmark single-thread score of 4330) suggests it can feed the GPU adequately, but the RTX 3090's 73rd percentile position means the GPU may become the limiting factor at lower resolutions where CPU overhead is higher. At 4K, the GPU's compute resources (35.58 TFLOPS FP32) will dominate the workload, making the GPU the primary bottleneck. The data implies a balanced pairing where neither component consistently limits the other, but rather the workload determines which side constrains performance.

# Gaming Performance

No measured FPS rows exist for this exact CPU+GPU combination — the FACT PACK contains no measuredFps data. All frame rate discussions below are estimates derived from the benchmark scores of each component, and should be treated as directional rather than definitive.

The RTX 3090's benchmark scores paint a picture of a capable 4K gaming GPU. Its 3DMark Steel Nomad DX12 score of 5118 and passmark_g3d score of 26645 indicate strong DirectX 12 performance, while the geekbench_vulkan score of 53927 suggests Vulkan titles will run well. The GPU's 24 GB of GDDR6X memory with 936.2 GB/s bandwidth provides ample headroom for high-resolution textures and ray tracing workloads, which are memory-intensive.

The CPU's gaming-relevant scores include a 3DMark single-thread score of 1121 and a Cinebench R23 single-core score of 5203, both indicating strong per-core performance for game logic and draw call processing. The 16 cores and 24 threads with a 5.50 GHz boost clock mean the CPU can handle background tasks while gaming without introducing stutter.

For 1080p ultra settings, the CPU's single-thread strength should allow high frame rates, but the GPU's 73rd percentile position relative to all GPUs means it may not sustain the highest refresh rates in the most demanding titles. At 1440p, the balance shifts toward the GPU, with its 35.58 TFLOPS FP32 compute and 189.8 GPixel/s pixel rate providing solid frame rates in most games. At 4K ultra, the GPU becomes the clear focus, with its 24 GB memory capacity ensuring texture quality doesn't degrade, though frame rates will depend heavily on the specific title and its optimization.

The absence of measured FPS data means these are estimates, but the component scores suggest this pairing is best suited for high-refresh 1440p gaming or playable 4K gaming rather than extreme competitive frame rates at 1080p.

# CPU Analysis

The Intel Core i9-12900KS is a 16-core, 24-thread processor based on the Alder Lake architecture, built on Intel's 10 nm process with a die size of 215 mm². Its hybrid design combines Performance cores and Efficiency cores, though the FACT PACK does not specify the exact core distribution. The base clock of 3.40 GHz boosts to 5.50 GHz, and the CPU is multiplier-unlocked for overclocking.

The cache hierarchy comprises 80 KB of L1 per core, 1.25 MB of L2 per core, and 30 MB of shared L3 cache. This L3 capacity is significant for gaming and productivity workloads, as it reduces memory latency by keeping frequently accessed data closer to the cores. The memory controller supports both DDR4 and DDR5 in dual-channel configuration, with a memory bandwidth of 76.8 GB/s, and ECC memory is supported.

Benchmark results reveal the CPU's character. The Cinebench R23 multicore score of 36859 and single-core score of 5203 show strong performance in both parallel and serial workloads. The Geekbench multicore score of 18538 and single-core of 2408 align with this picture. The Passmark multithread score of 43698 and single-thread of 4330 confirm the CPU's balanced design — it is not a single-thread specialist, nor a pure multi-core workhorse, but rather a versatile processor that handles both well.

The 3DMark thread scaling data is particularly revealing. The 2-thread score of 2212 doubles to 4320 at 4 threads (95% scaling), then adds 82% more at 8 threads (7872), and 31% more at 16 threads (10316). The jump to max threads (11897) adds only 15%, indicating the Efficiency cores contribute to multi-threaded workloads but with reduced per-thread performance. This suggests the CPU's real-world multi-threaded performance is driven primarily by the Performance cores, with Efficiency cores handling background tasks or lightly-threaded workloads.

The passmark data encryption score of 31403 and data compression score of 563709 indicate strong performance in security and data-heavy workloads, while the extended instructions score of 35089 shows the CPU handles SIMD and other advanced instruction sets effectively. The floating point math score of 111429 and integer math score of 147575 reveal a CPU that is slightly stronger in integer operations, which is typical for gaming and general productivity.

The CPU's 89th percentile ranking among all CPUs places it just 0.1% behind the AMD EPYC 4344P, 0.5% ahead of the Intel Core i5-14600, and 1.2% ahead of the AMD Ryzen 5 7500X3D. This tight grouping shows the i9-12900KS is competitive with modern mid-range and server processors, though it does not lead the pack.

# FAQ

Q: What is the combined percentile ranking of this CPU+GPU pairing?

A: The combined percentile is 81, which places this build in the top fifth of all desktop configurations in the database.

Q: How does the CPU compare to its nearest rival, the AMD EPYC 4344P?

A: The i9-12900KS has an average benchmark score of 45094, which is 0.1% lower than the EPYC 4344P's 45122. This is a negligible difference in practical terms.

Q: What is the GPU's average benchmark score and its nearest rival?

A: The RTX 3090 has an average benchmark score of 27565. Its nearest rival is the NVIDIA GeForce RTX 4070 Mobile with a score of 27435, putting the RTX 3090 0.5% ahead.

Q: Does the CPU support ECC memory?

A: Yes, the Intel Core i9-12900KS supports ECC memory, which is unusual for a consumer desktop processor and could benefit workstation builds.

Q: What is the CPU's boost clock and how many cores does it have?

A: The CPU boosts to 5.50 GHz and has 16 cores with 24 threads, using the Alder Lake hybrid architecture.

Q: What is the suggested power supply for the RTX 3090?

A: The suggested PSU for the RTX 3090 is 750 W, and the GPU has a TDP of 350 W.

Q: What is the GPU's memory configuration?

A: The RTX 3090 has 24 GB of GDDR6X memory on a 384-bit bus, providing 936.2 GB/s of bandwidth.

# Benchmark Performance

The CPU's average benchmark score is 45094, placing it in the 89th percentile of all CPUs. Its nearest rival, the AMD EPYC 4344P, scores 45122, a 0.1% difference that puts the i9-12900KS slightly behind. The Intel Core i5-14600 trails by 0.5% with a score of 44889, while the AMD Ryzen 5 7500X3D is 1.2% behind at 44573, and the Intel Core Ultra X9 388H is 1.4% behind at 44466. This grouping shows the i9-12900KS performs within a narrow band of modern processors, neither dominating nor being dominated.

The GPU's average benchmark score is 27565, placing it in the 73rd percentile of all GPUs. Its nearest rival is the NVIDIA GeForce RTX 4070 Mobile at 27435, which is 0.5% behind. The AMD Radeon RX 6700 XT scores 27425, also 0.5% behind, while the AMD Radeon Pro Vega 20 is 1% ahead at 27839, and the AMD Radeon RX 7800M is 1.1% ahead at 27883. The RTX 3090 sits in the middle of this cluster, neither leading nor trailing significantly.

The combined percentile of 81 reflects a pairing where the CPU is stronger relative to its peers than the GPU is to its own peers. The CPU's 89th percentile pulls the combined score up, while the GPU's 73rd percentile drags it down. This suggests the GPU is the weaker link in this pairing, though both components are competent in their respective fields.

In specific benchmarks, the CPU's Cinebench R23 multicore score of 36859 and single-core of 5203 are strong, while the GPU's 3DMark Steel Nomad DX12 score of 5118 and passmark_g3d of 26645 are respectable but not class-leading. The GPU's passmark_gpu_compute score of 15356 indicates solid compute performance for non-gaming workloads.

# Upgrade Path and Platform

The Intel Core i9-12900KS uses the Intel Socket 1700 platform, which supports both DDR4 and DDR5 memory in dual-channel configuration. The CPU's memory bandwidth of 76.8 GB/s is modest compared to modern platforms, suggesting that a memory upgrade could be a bottleneck in memory-intensive workloads. The socket supports PCIe Gen 5 with 16 lanes from the CPU, providing high-bandwidth connectivity for modern GPUs and NVMe storage.

The RTX 3090 uses a PCIe 4.0 x16 interface, which is backward compatible with the CPU's PCIe Gen 5 slots. The GPU's 350 W TDP and suggested PSU of 750 W mean the power supply is a critical consideration. A 750 W PSU provides headroom for the GPU and CPU combined, but overclocking the multiplier-unlocked CPU could push power demands higher.

The CPU's production status is Active, meaning it remains in production, while the GPU is End-of-life. This suggests the GPU is the component most likely to be replaced first in an upgrade cycle. The GPU's successor, the GeForce 40 series, exists, and the CPU's platform supports newer Intel processors, though specific compatibilities are not detailed in the data.

A sensible next upgrade would be the GPU, as its 73rd percentile ranking is the weaker component. The CPU's 89th percentile ranking means it has more headroom to drive a more powerful GPU. Alternatively, adding more memory or faster DDR5 could improve the CPU's effective performance, given its 76.8 GB/s bandwidth is a potential constraint.

The CPU's integrated UHD Graphics 770 provides a fallback display output if the discrete GPU fails or is removed, though it is not suitable for gaming. The platform's ECC memory support adds reliability for workstation use, but requires compatible ECC modules.

# Who Should Build It

This pairing targets users who need strong multi-threaded CPU performance alongside capable GPU compute. The CPU's Cinebench R23 multicore score of 36859 and Passmark multithread score of 43698 indicate it handles content creation, software compilation, and data processing well. The GPU's 24 GB memory and 35.58 TFLOPS FP32 compute appeal to 3D renderers, video editors, and machine learning practitioners.

Gamers at 1440p and 4K resolutions will find the RTX 3090's 24 GB memory and 936.2 GB/s bandwidth sufficient for high-resolution textures and ray tracing, though the GPU's 73rd percentile ranking means it is not the fastest available. The CPU's 5.50 GHz boost clock and strong single-thread performance (Passmark single-thread of 4330) ensure game logic runs smoothly.

Content creators working with video editing or 3D rendering will benefit from the CPU's 16 cores and 24 threads, with the passmark floating point math score of 111429 indicating good performance in physics and rendering calculations. The GPU's tensor cores and RT cores accelerate AI-based tasks and ray-traced rendering.

Software developers will appreciate the CPU's strong multi-threaded performance for compilation tasks, with the passmark data compression score of 563709 suggesting fast build times for large codebases. The ECC memory support adds stability for long-running build processes.

Students and small business workstations may find this pairing overkill for basic office tasks, but the CPU's integrated graphics provide a fallback, and the GPU's compute capabilities can handle data analysis or CAD workloads. The CPU's 89th percentile ranking ensures it will remain relevant for several years, while the GPU's End-of-life status suggests it may need replacement sooner.

# Build Overview

This is a desktop-class build pairing the Intel Core i9-12900KS with the NVIDIA GeForce RTX 3090. The CPU, released in April 2022 with a launch MSRP of $739, is an Active production part, while the GPU, released in August 2020 with a launch MSRP of 1,499 USD, is End-of-life.

The combined percentile of 81 places this build in the upper fifth of all configurations, though the gap between the CPU's 89th percentile and GPU's 73rd percentile indicates an imbalance. The CPU is the stronger component, and the GPU, while capable, is the limiting factor in this pairing.

The build's overall tier is that of a high-end desktop workstation or enthusiast gaming rig from the 2020-2022 era. The CPU's 16 cores and 24 threads with a 5.50 GHz boost clock provide strong performance for both gaming and productivity, while the GPU's 24 GB memory and 35.58 TFLOPS FP32 compute handle demanding graphics and compute workloads.

The i9-12900KS is a special edition processor, as indicated by the "KS" suffix, which typically denotes higher binning and boost clocks. Its 5.50 GHz boost clock is among the highest available, and the multiplier-unlocked design allows further overclocking. The GPU's triple-slot design and 336 mm length require a spacious case, and the 1x 12-pin power connector may require an adapter for standard PSUs.

# GPU Analysis

The NVIDIA GeForce RTX 3090 is based on the GA102 chip using the Ampere architecture, built on Samsung's 8 nm process with 28,300 million transistors on a 628 mm² die. The GPU has 10496 shading units, 328 texture mapping units, and 112 raster operations pipelines, along with 82 RT cores and 328 tensor cores.

Its 24 GB of GDDR6X memory on a 384-bit bus provides 936.2 GB/s of bandwidth, with a memory clock of 1219 MHz (19.5 Gbps effective). The base clock is 1395 MHz, boosting to 1695 MHz. The GPU's pixel rate is 189.8 GPixel/s, and its texture rate is 556.0 GTexel/s.

Compute performance is rated at 35.58 TFLOPS for both FP32 and FP16 (1:1 ratio). The GPU supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, making it compatible with modern games and applications. Display outputs include 1x HDMI 2.1 and 3x DisplayPort 1.4a.

The benchmark scores reveal a GPU that performs well but is not top-tier. The 3DMark Steel Nomad DX12 score of 5118 and passmark_g3d score of 26645 indicate solid gaming performance. The geekbench_opencl score of 172758 shows strong compute for OpenCL workloads, while the geekbench_vulkan score of 53927 confirms Vulkan compatibility and performance.

The passmark_gpu_compute score of 15356 suggests the GPU handles compute tasks well, which is relevant for rendering and machine learning. The DirectX 10 score of 182, DirectX 11 score of 220, DirectX 12 score of 110, and DirectX 9 score of 268 are legacy benchmarks that indicate the GPU's performance across older APIs.

The GPU's 73rd percentile ranking and its proximity to rivals like the RTX 4070 Mobile (0.5% ahead) and RX 6700 XT (0.5% ahead) suggest it is a mid-to-high-end GPU that has been surpassed by newer models. Its 24 GB memory remains a differentiator, as most rivals in its performance band have less VRAM.

# Usage Scenarios

High-refresh gaming: The CPU's strong single-thread performance (Passmark single-thread of 4330) supports high frame rates, but the GPU's 73rd percentile ranking means it may not sustain the highest refresh rates at 1080p. At 1440p, the RTX 3090's 24 GB memory and 35.58 TFLOPS compute provide a good balance for 144Hz gaming in most titles.

Streaming: The CPU's 16 cores and 24 threads handle encoding and streaming overhead without impacting game performance, while the GPU's tensor cores can accelerate AI-based encoding features. The combined percentile of 81 indicates this build can handle simultaneous gaming and streaming workloads.

Video editing: The CPU's Cinebench R23 multicore score of 36859 accelerates video rendering and export, while the GPU's 24 GB memory and passmark_gpu_compute score of 15356 assist with effects and color grading. The 936.2 GB/s bandwidth ensures fast access to video buffers.

3D rendering: The GPU's 82 RT cores and 35.58 TFLOPS FP32 compute make it suitable for ray-traced rendering, while the CPU's 16 cores handle scene processing and geometry. The 24 GB memory prevents out-of-memory errors in complex scenes, and the passmark floating point math score of 111429 supports physics simulations.

Software development: The CPU's Passmark multithread score of 43698 and data compression score of 563709 speed up compilation and build processes. The ECC memory support adds stability for long-running builds, and the 16 cores handle parallel compilation efficiently.

Student and office work: This build is overkill for basic productivity, but the CPU's integrated UHD Graphics 770 provides a fallback, and the 89th percentile CPU ranking ensures responsiveness. The GPU's compute capabilities can handle data analysis or CAD workloads if needed, though the 350 W TDP makes this an inefficient choice for purely office tasks.