SYSTEM ANALYZER

Rate My PC: Intel Core i9-13900KF + NVIDIA GeForce RTX 5090 D

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

97 / 100
ULTIMATE READY

Apex Performer

Top 3% 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
96%
VS
GPU
98%
PROCESSOR

Intel Core i9-13900KF

61,841 Benchmark Score
Top 4% Market Ranking
View Full Specs →
GRAPHICS CARD

NVIDIA GeForce RTX 5090 D

77,712 Benchmark Score
Top 2% 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

GPU Analysis — VRAM, bandwidth, clocks, RT/tensor hardware, what the benchmark scores mean for rendering

The NVIDIA GeForce RTX 5090 D is a dual-slot, 304 mm card built on the Blackwell 2.0 architecture with a 5 nm process from TSMC. It packs 21,760 shading units, 680 texture mapping units, and 176 raster operation pipelines. The memory subsystem is the headline feature: 32 GB of GDDR7 across a 512-bit bus delivers 1.79 TB/s of bandwidth. That is a massive pool for both high-resolution textures and large compute workloads. The card’s memory clock runs at 1750 MHz, or 28 Gbps effective. With a base clock of 2017 MHz and a boost of 2407 MHz, the card achieves a pixel rate of 423.6 GPixel/s and a texture rate of 1,636.8 GTexel/s. FP32 throughput is rated at 104.8 TFLOPS, with FP16 matching at 104.8 TFLOPS (1:1). The RT cores number 170, and the tensor cores number 680. This is a GPU built for heavy ray tracing and AI-accelerated workloads, not just rasterization.

In synthetic benchmarks, the RTX 5090 D posts a 3DMark Steel Nomad DX12 score of 14,326. That result places it in the 92nd percentile of all GPUs, meaning it outperforms roughly 92% of the database’s tracked graphics cards. The Geekbench OpenCL score is 310,674, and the Vulkan score is 376,915. Passmark G3D score is 44,065, with a GPU compute score of 28,396. The DirectX 12 Passmark score is 219, while DirectX 11 is 371 and DirectX 10 is 231. These numbers indicate that the card is heavily optimized for modern APIs and compute-heavy tasks. The G2D score of 1,487 is less relevant for gaming but indicates solid 2D acceleration. For rendering, the combination of 32 GB VRAM, 1.79 TB/s bandwidth, and 104.8 TFLOPS FP32 means large scenes, high-res textures, and complex lighting can be handled without spilling to system memory. The 170 RT cores and 680 tensor cores suggest real-time ray tracing and DLSS-style upscaling will be strong, though specific frame rates are not measured in the data.

The nearest rivals in the database provide context. The AMD Radeon RX 6650M XT scores 76,904, which is 1.1% lower than the RTX 5090 D’s average benchmark score of 77,712. The AMD Radeon RX 6850M XT scores 78,940, putting it 1.6% higher. The NVIDIA Tesla P100 PCIe 12 GB and 16 GB versions score 79,396 and 79,605, respectively, which are 2.1% and 2.4% higher. These deltas are small, but the RTX 5090 D’s consumer feature set — 32 GB GDDR7, dedicated RT cores, modern API support (DirectX 12 Ultimate, Vulkan 1.4) — makes it better suited for gaming and content creation than the compute-oriented Tesla cards. The data suggests the RTX 5090 D is a top-tier consumer GPU, but the benchmark scores alone do not capture the advantage in ray tracing or tensor workloads, which are not directly measured here.

Benchmark Performance

The Intel Core i9-13900KF and NVIDIA GeForce RTX 5090 D combination sits at the 93rd combined percentile across all desktop builds in the database. The CPU’s average benchmark score is 61,841, and the GPU’s is 77,712. No measured FPS rows exist for this exact combination — the FACT PACK contains no measuredFps data. The performance picture must be inferred from synthetic scores.

The CPU scores are strong across the board. In 3DMark, the i9-13900KF scores 1,188 in single-thread, 2,353 in 2-thread, 4,643 in 4-thread, 8,510 in 8-thread, 11,177 in 16-thread, and 15,405 in max-thread tests. Cinebench R23 multi-core is 48,855, and single-core is 6,897. Geekbench multi-core is 22,486, single-core 2,668. Passmark multi-thread is 57,729, single-thread 4,584. These scores place the CPU in the 93rd percentile of all CPUs. The nearest rival, the Intel Core Ultra 7 270HX Plus, has an average score of 61,834, a 0% delta. The Intel Core i9-13900K scores 61,766, 0.1% lower. The i9-13900T scores 61,723, 0.2% lower. The Intel Xeon 636 scores 61,360, 0.8% lower. The KF variant is essentially tied with the K version, which makes sense given the unlocked multiplier and similar architecture.

The GPU’s 92nd percentile ranking, combined with the CPU’s 93rd percentile, creates a balanced high-end pairing. The combined picture is a system that will not leave obvious performance on the table in most workloads. The CPU’s multi-threaded scores (Cinebench R23 48,855) suggest it can feed the GPU in CPU-bound scenarios, while the GPU’s massive compute throughput (104.8 TFLOPS FP32) will dominate GPU-bound tasks. The 3DMark Steel Nomad score of 14,326 indicates strong DX12 gaming performance, though it is a synthetic measure. The Passmark G3D score of 44,065 reinforces this. The data does not include game-specific FPS numbers, so all gaming conclusions are estimates based on these synthetic results.

CPU Analysis

The Intel Core i9-13900KF is a 24-core, 32-thread processor based on Raptor Lake architecture, built on Intel’s 10 nm process. The die size is 257 mm². It has a base clock of 3.00 GHz and a boost clock of 5.80 GHz. The cache hierarchy includes 80 KB L1 per core, 2 MB L2 per core, and 36 MB shared L3. The CPU supports DDR4 and DDR5 memory in dual-channel mode, with ECC support available. It uses the Intel Socket 1700 and provides 20 PCIe Gen 5 lanes from the CPU. The TDP is 125 W, and the multiplier is unlocked, allowing overclocking. The launch MSRP is $564. The processor was released on 2022-09-26.

In single-threaded performance, the i9-13900KF scores 1,188 in 3DMark single-thread, 6,897 in Cinebench R23 single-core, and 2,668 in Geekbench single-core. These are strong numbers for a desktop CPU, indicating excellent responsiveness in lightly threaded tasks like web browsing, office applications, and older games. The boost clock of 5.80 GHz is a key contributor here. Multi-threaded performance is where this chip shines. Cinebench R23 multi-core is 48,855, which is about 7x the single-core score, reflecting the 24-core/32-thread design. Geekbench multi-core is 22,486. Passmark integer math is 206,859, floating-point math is 150,869, and extended instructions score 46,084. Data compression scores 786,218, and data encryption scores 46,186. These numbers suggest heavy compute workloads — video encoding, 3D rendering, software compilation — will scale well with the core count.

The nearest rivals are all within 0.8% of the i9-13900KF’s average score. The Core Ultra 7 270HX Plus matches at 0% delta, the i9-13900K is 0.1% lower, the i9-13900T is 0.2% lower, and the Xeon 636 is 0.8% lower. The KF variant is effectively identical to the K in performance, but without integrated graphics. For users with a discrete GPU, this is a non-issue. The processor’s 93rd percentile ranking means it outperforms most CPUs in the database, but the close rival deltas indicate that the top end is crowded. The 5.80 GHz boost clock is the differentiator in single-thread workloads, while the 24 cores drive multi-thread results. The combination of high clocks and many cores makes this CPU versatile across gaming and productivity.

Who Should Build It

This combination of the Intel Core i9-13900KF and NVIDIA GeForce RTX 5090 D targets users who demand maximum performance in both CPU- and GPU-bound tasks. Gamers at 4K resolution with high refresh rate monitors will benefit most from the RTX 5090 D’s 32 GB VRAM and 1.79 TB/s bandwidth, as these are the specs that handle ultra-high texture packs and ray tracing without stutter. The CPU’s single-thread score of 1,188 in 3DMark and 6,897 in Cinebench R23 ensures that even at lower resolutions where the CPU matters more, frame rates will not be artificially limited. At 1440p, the CPU’s strong single-thread performance keeps up with the GPU’s rasterization power, though the exact FPS is not measured.

Content creators are a clear target. Video editors working with 8K footage or long timelines will use the CPU’s 24 cores and 32 threads, evidenced by the Cinebench R23 multi-core score of 48,855. The GPU’s 32 GB VRAM allows for large compositing projects and GPU-accelerated effects without memory pressure. 3D renderers using GPU acceleration will see the FP32 throughput of 104.8 TFLOPS and the tensor cores for AI denoising. Software developers compiling large codebases will benefit from the Passmark integer math score of 206,859 and multithread score of 57,729. The ECC memory support is a plus for data integrity in long compute jobs.

Students in engineering or data science fields, where workloads involve simulation or machine learning, will find the tensor cores and 32 GB VRAM useful. Small business workstations running virtualization or database workloads will use the CPU’s 32 threads and the GPU’s compute capability for parallel processing. The build is overkill for basic office work, but for any task that scales with cores or GPU throughput, it is a top-tier choice. The 93rd combined percentile confirms that this pairing is among the fastest in the database, so it is for users who prioritize performance over other concerns.

Usage Scenarios

High-refresh gaming: The RTX 5090 D’s 3DMark Steel Nomad score of 14,326 and Passmark G3D of 44,065 indicate it can drive high frame rates at high resolutions. The CPU’s single-thread score of 1,188 in 3DMark ensures minimal bottleneck in CPU-limited scenes. Expect smooth gameplay at 1440p and 4K, though exact FPS is an estimate since no measured data exists.

Streaming: The CPU’s 24 cores and 32 threads, reflected in the Cinebench R23 multi-core score of 48,855, can handle both game encoding and streaming software simultaneously. The GPU’s tensor cores and 32 GB VRAM support hardware encoding and AI-enhanced video quality. The 125 W TDP of the CPU leaves thermal headroom for sustained loads.

Video editing: The CPU’s Passmark multithread score of 57,729 and integer math of 206,859 accelerate timeline rendering and effects processing. The GPU’s 32 GB VRAM handles 4K and 8K footage with multiple layers. The 1.79 TB/s bandwidth moves large frames quickly.

3D rendering: The GPU’s FP32 throughput of 104.8 TFLOPS and 170 RT cores accelerate both raster and ray-traced renders. The CPU’s Cinebench R23 multi-core of 48,855 handles physics and geometry preparation. The 32 GB VRAM allows entire scenes to reside on the GPU.

Software development: The CPU’s Passmark integer math of 206,859 and multithread score of 57,729 reduce compile times. The 36 MB L3 cache keeps working sets close to the cores. The GPU is less relevant here but available for testing or compute tasks.

Student and office work: The CPU’s single-thread score of 4,584 in Passmark ensures snappy response in spreadsheets and browsers. The GPU is overkill for word processing, but the system will never feel slow. This is a workstation that handles any academic software.

Gaming Performance

There are no measured FPS rows for this exact combination — the FACT PACK contains no measuredFps data. All gaming performance figures are estimates based on the synthetic benchmark scores. The RTX 5090 D’s 3DMark Steel Nomad DX12 score of 14,326 places it in the 92nd percentile of GPUs. The Passmark DirectX 12 score of 219 and Vulkan 1.4 API support indicate strong modern API performance. The CPU’s single-thread 3DMark score of 1,188 and Cinebench R23 single-core of 6,897 suggest it will not bottleneck the GPU in most games.

At 4K ultra settings, the GPU’s 32 GB VRAM and 1.79 TB/s bandwidth are sufficient for the highest texture quality and ray tracing effects. The 104.8 TFLOPS FP32 throughput handles heavy shading loads. At 1440p, the CPU’s strong single-thread performance becomes more relevant, and the 5.80 GHz boost clock should keep frame rates high. At 1080p, the CPU may become the limiting factor in some titles, but the 24 cores and high boost clock mitigate this. The 170 RT cores suggest ray tracing performance is strong, but the lack of measured FPS means these are projections, not results.

Balance and Bottleneck

The data shows a well-balanced pairing. The CPU’s 93rd percentile and GPU’s 92nd percentile are nearly identical, indicating neither component is dramatically stronger than the other on average. The combined percentile is 93, suggesting the system performs at the level of its strongest component. In CPU-bound workloads like data compression (Passmark score 786,218) or encryption (46,186), the i9-13900KF is the workhorse. In GPU-bound workloads like 3DMark Steel Nomad (14,326) or Geekbench Vulkan (376,915), the RTX 5090 D takes over.

The bottleneck shifts based on the task. For gaming at 1080p, the CPU’s single-thread score of 1,188 in 3DMark is sufficient, but the GPU’s massive throughput may be underutilized. At 4K, the GPU’s 1.79 TB/s bandwidth and 32 GB VRAM are the primary drivers, and the CPU’s multi-thread score of 15,405 in 3DMark max-thread reduces the chance of a CPU-side stall. For rendering, the GPU’s FP32 of 104.8 TFLOPS dominates, while the CPU’s Cinebench R23 multi-core of 48,855 handles scene setup. The close rival deltas (0% to 0.8% for the CPU, -2.4% to 1.1% for the GPU) mean that small changes in workload can flip which component is the limiting factor. Overall, this is a system where both components are at the same tier, so neither is a clear bottleneck.

FAQ

Q: What is the CPU’s core and thread count?

A: The Intel Core i9-13900KF has 24 cores and 32 threads.

Q: How much VRAM does the RTX 5090 D have, and what type?

A: The RTX 5090 D has 32 GB of GDDR7 memory on a 512-bit bus.

Q: What is the CPU’s boost clock speed?

A: The i9-13900KF boosts up to 5.80 GHz.

Q: Does the CPU support DDR4 memory?

A: Yes, the i9-13900KF supports both DDR4 and DDR5 in dual-channel mode.

Q: What is the GPU’s FP32 performance?

A: The RTX 5090 D achieves 104.8 TFLOPS in FP32.

Q: What is the combined percentile of this build?

A: This CPU-GPU combination sits at the 93rd combined percentile.

Q: Is there measured FPS data for this combination?

A: No, the FACT PACK contains no measured FPS data for this exact pairing.

Upgrade Path and Platform

The Intel Core i9-13900KF uses the Intel Socket 1700, which supports DDR4 and DDR5 memory in dual-channel mode. The CPU provides 20 PCIe Gen 5 lanes, and the GPU uses PCIe 5.0 x16. The power requirements are significant: the CPU has a 125 W TDP, and the GPU has a 575 W TDP. The suggested PSU for the GPU alone is 950 W. The GPU uses a single 16-pin power connector and is dual-slot wide, measuring 304 mm in length, 137 mm in height, and 48 mm in width. This requires a case with sufficient clearance and a PSU with the appropriate cables.

A sensible next upgrade would be to increase memory capacity beyond the current support, as the CPU supports both DDR4 and DDR5, allowing users to choose the best available. The storage subsystem can be expanded via the 20 PCIe Gen 5 lanes, which support the fastest NVMe SSDs. For future GPU upgrades, the PCIe 5.0 x16 slot is current-generation, so it is not a bottleneck. The CPU’s unlocked multiplier allows overclocking to extend its lifespan, though the 125 W TDP may require a capable cooler. The platform is mature, with the CPU being Active in production, so BIOS updates and compatibility are well-established. If a user wants more CPU performance, the nearest rival, the Core Ultra 7 270HX Plus, is only 0% different in average score, so a meaningful CPU upgrade would require a new socket. The GPU has a successor listed as GeForce 60, so an upgrade path exists, but the current card’s 32 GB VRAM and 104.8 TFLOPS are already top-tier. The PSU headroom is the main constraint; the 950 W suggested PSU leaves little room for high-power peripherals, so a larger PSU is advisable for any future upgrades.