SYSTEM ANALYZER

Rate My PC: AMD Ryzen 7 8700F + NVIDIA GeForce RTX 5090 D

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
89%
VS
GPU
98%
PROCESSOR

AMD Ryzen 7 8700F

30,746 Benchmark Score
Top 11% 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

# Balance and Bottleneck

The pairing of an AMD Ryzen 7 8700F with an NVIDIA GeForce RTX 5090 D creates an intriguing asymmetry that demands scrutiny. The CPU sits at the 82nd percentile among all processors, while the GPU commands the 92nd percentile among all graphics cards. That ten-point percentile gap is the first quantitative hint that this is a system where the processor will frequently be the limiting factor in GPU-bound scenarios.

Looking at the CPU's multi-threaded capabilities, the 3DMark 16-thread score of 7883 and max-thread score of 7861 are nearly identical, indicating that the 8-core/16-thread configuration saturates its performance ceiling quickly. The 4-thread score of 3839 and 8-thread score of 6559 show scaling that is strong through eight threads but flattens beyond that point. This suggests that heavily threaded workloads, such as modern game engines that leverage 8+ cores, will extract nearly all available CPU performance, but the GPU will still wait on the processor in many frames.

The GPU's raw compute output, with an FP32 throughput of 104.8 TFLOPS and a texture rate of 1,636.8 GTexel/s, dwarfs what the CPU can feed in gaming scenarios. The pixel rate of 423.6 GPixel/s further emphasizes that the RTX 5090 D can generate frames far faster than the 8700F's single-thread score of 1008 in 3DMark can direct. In lighter CPU-load scenarios, the GPU will stretch its legs; in complex scenes with heavy physics or AI simulation, the CPU will throttle the pipeline.

The memory bandwidth situation reinforces this imbalance. The CPU's dual-channel DDR5 support yields 83.2 GB/s, while the GPU's 512-bit GDDR7 interface delivers 1.79 TB/s. That's a 21.5x difference in available memory bandwidth, which means data transfer bottlenecks will almost always originate from the CPU side when the GPU is waiting for instructions or geometry data.

For productivity workloads, the picture shifts slightly. The CPU's PassMark multi-thread score of 30893 and Cinebench R23 multi-core score of 26646 are respectable but not class-leading. The GPU's OpenCL score of 310674 and Vulkan score of 376915 in Geekbench show that compute-heavy tasks like rendering or simulation will be massively GPU-accelerated, but the CPU's 16-thread ceiling will cap certain physics or logic simulations that don't offload well to the GPU.

The bottleneck analysis points to one clear conclusion: this is a GPU-limited system in pure rasterization and ray tracing, but a CPU-limited system in frame generation scenarios where the processor must coordinate multiple GPU tasks simultaneously. The RTX 5090 D's 170 ray tracing cores and 680 tensor cores can process lighting and DLSS data far faster than the 8700F can issue the draw calls.

# Benchmark Performance

The CPU's average benchmark score of 30746 places it at the 82nd percentile of all CPUs, which is a solid mid-to-upper tier position. Its nearest rivals show remarkably tight competition: the AMD Ryzen 5 PRO 8645HS scores 30879 (0.4% higher), the Intel Core i5-13600H scores 30548 (0.6% lower), and the Intel Core Ultra 5 225T scores 30468 (0.9% lower). The 8700F essentially sits in a dead heat with these mobile and low-power desktop parts, which is notable because the 8700F is a desktop chip with a 65W TDP.

Single-thread performance tells a more nuanced story. The Geekbench single-core score of 2290 and Cinebench R23 single-core score of 3761 indicate strong per-core efficiency from the Zen 4 architecture. The 3DMark single-thread score of 1008 and 2-thread score of 1989 show that the processor can handle lightly threaded tasks with composure. However, these numbers are not exceptional for a desktop part in 2024, which suggests the 8700F's positioning is more about efficiency than raw speed.

The GPU's benchmark results are where this system separates from the pack. The 3DMark Steel Nomad DX12 score of 14326 is a strong indicator of modern DirectX 12 gaming performance. The PassMark G3D score of 44065 and G2D score of 1487 show that the card excels at 3D rendering while maintaining competent 2D operations. The Geekbench Vulkan score of 376915 is particularly impressive, suggesting excellent low-level API performance that will benefit modern game engines.

The GPU's average benchmark score of 77712 places it at the 92nd percentile, but its nearest rivals are surprising: the AMD Radeon RX 6650M XT scores 76904 (1.1% lower), while the RX 6850M XT scores 78940 (1.6% higher). These are mobile GPUs with significantly lower power envelopes, yet they trade blows with the RTX 5090 D in average benchmark terms. This suggests that the RTX 5090 D's massive specifications — 32 GB GDDR7, 21760 shading units, and 104.8 TFLOPS — may not translate to proportional benchmark wins in every test, possibly due to driver maturity or thermal constraints.

The combined percentile for this CPU+GPU pairing is 87, which places the system in the upper echelon of desktop builds. The CPU's 82nd percentile and GPU's 92nd percentile combine to a system that will handle any modern workload, but the discrepancy between the two components' positions is a recurring theme.

# Upgrade Path and Platform

The AMD Ryzen 7 8700F uses the AMD Socket AM5 platform, which provides a clear upgrade path within the same motherboard. The CPU supports DDR5 memory in a dual-channel configuration, yielding 83.2 GB/s of bandwidth. It also offers PCIe Gen 4 with 20 lanes from the CPU, which is sufficient for a single high-end GPU and one or two NVMe drives.

The CPU's 65W TDP is modest, which means the AM5 platform's power delivery won't be stressed by the processor itself. However, the RTX 5090 D is a different story entirely: its 575W TDP and suggested PSU of 950W demand a robust power supply. The GPU requires a single 16-pin power connector, which simplifies cabling but requires a PSU with that connector natively or a high-quality adapter.

The platform's memory support for DDR5 with ECC disabled means that users building a workstation for error-sensitive tasks will need to rely on the GPU's error correction capabilities instead. The CPU's 16 MB of shared L3 cache and 1 MB L2 per core are sufficient for gaming but may feel constrained in server-style workloads.

The upgrade path for this build is straightforward: the AM5 socket supports future Ryzen generations, and the PCIe 5.0 x16 interface on the GPU (though the CPU only provides Gen 4 lanes) means the graphics card can be moved to a newer platform without losing bandwidth. The 950W suggested PSU provides headroom for a future CPU upgrade that draws more power than the current 65W part, though a flagship CPU could push the envelope.

A sensible next upgrade would be a CPU with more cores or higher clocks, as the GPU has ample headroom to benefit from a stronger processor. The RTX 5090 D's 32 GB VRAM and 1.79 TB/s bandwidth will remain relevant for years, making the GPU the component to keep while the CPU is swapped.

# Gaming Performance

No measured FPS rows exist for this exact combination — the FACT PACK contains no measuredFps data. The following discussion is therefore framed as estimates derived from the benchmark scores, not empirical measurements. The CPU's 82nd percentile and GPU's 92nd percentile, combined with the 87th combined percentile, provide a basis for these projections.

At 1080p, the system will likely be CPU-bound in most titles. The 8700F's single-thread score of 1008 in 3DMark and PassMark single-thread score of 3872 suggest that frame rates in esports titles could reach very high levels, but the GPU's massive throughput will be underutilized. The 3DMark 2-thread score of 1989 indicates that lightly threaded games will run smoothly, but the processor may cap maximum FPS in the 200-300 range depending on the title.

At 1440p, the balance shifts toward the GPU. The RTX 5090 D's 3DMark Steel Nomad score of 14326 suggests it can handle modern AAA games at high refresh rates, likely pushing 144Hz monitors to their limits in most titles. The CPU's 8-thread score of 6559 in 3DMark indicates that eight cores will be fully utilized, which is typical for modern game engines. The 16 MB L3 cache may cause some frame pacing issues in games that require larger working sets, but this is speculative.

At 4K, the GPU will dominate the workload. The 104.8 TFLOPS of FP32 compute and 423.6 GPixel/s pixel rate are more than sufficient for 4K rendering, and the 32 GB GDDR7 memory eliminates any VRAM capacity concerns. The CPU's role becomes secondary, and the system should deliver consistently high frame rates at this resolution, likely exceeding 60 FPS in even the most demanding titles.

Ray tracing performance will be a strength, given the 170 RT cores and the GPU's architecture. The Vulkan score of 376915 suggests that the card excels at the low-level API calls that ray tracing requires. DLSS, powered by the 680 tensor cores, will further boost frame rates in supported titles.

The overall gaming picture is of a system that can handle any resolution, but with diminishing returns at lower resolutions where the CPU becomes the bottleneck.

# Who Should Build It

This system targets gamers who prioritize 4K or high-refresh 1440p gaming, where the RTX 5090 D's strengths are most apparent. The GPU's 92nd percentile ranking and 32 GB VRAM make it ideal for those who want to max out every setting without compromise. The CPU's 82nd percentile is adequate for these scenarios, though not the absolute best available.

Content creators who work with video editing, 3D rendering, or machine learning will find the GPU's compute capabilities — 104.8 TFLOPS FP32 and 28396 PassMark GPU compute score — to be transformative. The CPU's 16 threads and 26646 Cinebench R23 multi-core score provide enough processing power for asset preparation and timeline management, while the GPU accelerates the heavy lifting.

Software developers building games or graphics applications will benefit from the Vulkan score of 376915 and DirectX 12 Ultimate support, which allows them to test against modern API features. The CPU's PassMark data compression score of 378160 and random string sorting score of 45425 indicate strong performance for build tools and code compilation.

Students in engineering or computer science programs will find the system overkill for coursework but useful for research projects involving GPU computing. The small business workstation use case is less compelling, given the GPU's power draw and cost, but the CPU's 65W TDP and efficient Zen 4 architecture make it a reasonable office machine when paired with a less demanding GPU.

# GPU Analysis

The NVIDIA GeForce RTX 5090 D is built on the Blackwell 2.0 architecture using a 5 nm process at TSMC, with 92,200 million transistors on a 750 mm² die. This is a massive chip, and the transistor density of 122.9M per mm² reflects a dense but power-hungry design. The 575W TDP is among the highest for consumer GPUs, necessitating the 950W suggested PSU.

The memory subsystem is a highlight: 32 GB of GDDR7 on a 512-bit bus yields 1.79 TB/s of bandwidth. This is more than sufficient for any current game or render workload, and the capacity ensures that even future titles with massive texture packs will fit comfortably. The memory clock of 1750 MHz (28 Gbps effective) is fast enough to feed the 21760 shading units without starving them.

The GPU's 680 TMUs and 176 ROPs deliver a texture rate of 1,636.8 GTexel/s and pixel rate of 423.6 GPixel/s. These figures place the card at the top of the consumer hierarchy, and the PassMark G3D score of 44065 confirms this positioning. The DirectX 12 score of 219 in PassMark may seem low, but this is a synthetic metric that doesn't reflect the card's actual DX12 capabilities as shown by the 3DMark Steel Nomad score of 14326.

The 170 RT cores and 680 tensor cores provide dedicated hardware for ray tracing and AI acceleration. The Geekbench Vulkan score of 376915 suggests that these cores are well-integrated and can be leveraged by modern APIs. The FP16 throughput of 104.8 TFLOPS (1:1 with FP32) is notable for machine learning inference tasks, though the PassMark GPU compute score of 28396 indicates that raw compute performance is strong but not the absolute peak.

The GPU's nearest rivals in benchmark terms are mobile parts, which is unusual. The RX 6650M XT (1.1% lower) and RX 6850M XT (1.6% higher) are laptop GPUs that trade blows with this desktop card in average scores. This suggests that the RTX 5090 D's performance is not fully realized in synthetic benchmarks, possibly due to driver overhead or the benchmark suite not scaling with the card's massive resources.

# CPU Analysis

The AMD Ryzen 7 8700F is an 8-core, 16-thread processor based on the Zen 4 architecture, codenamed Phoenix, built on a 4 nm process at TSMC. The 25,000 million transistors on a 178 mm² die represent a dense, efficient design that fits within a 65W TDP. The base clock of 4.10 GHz and boost clock of 5.00 GHz are competitive for the power envelope.

The cache hierarchy is modest: 64 KB L1 per core, 1 MB L2 per core, and 16 MB shared L3. The lack of 3D V-Cache and the relatively small L3 may impact gaming performance in cache-sensitive titles, but the PassMark data compression score of 378160 and integer math score of 100371 suggest that the CPU handles data-intensive tasks well.

The 3DMark benchmark scores show a clear scaling pattern: 1008 single-thread, 1989 for 2 threads, 3839 for 4 threads, 6559 for 8 threads, and 7883 for 16 threads. The jump from 8 to 16 threads is only 20%, indicating that the additional threads provide diminishing returns. The max-thread score of 7861 is nearly identical to the 16-thread score, confirming that the processor's scaling ceiling is reached at 16 threads.

Cinebench scores reinforce this: R23 multi-core of 26646 versus single-core of 3761 yields a 7.1x scaling factor across 16 threads, which is below the theoretical 16x but typical for a consumer chip with shared memory bandwidth. The Geekbench multi-core score of 13523 and single-core of 2290 show similar characteristics.

The CPU's nearest rival, the AMD Ryzen 5 PRO 8645HS, scores 0.4% higher on average, which is remarkable because that is a mobile processor. The Intel Core i5-13600H is 0.6% lower, and the Core Ultra 5 225T is 0.9% lower. This places the 8700F in a tight cluster of mid-range parts, despite being a desktop chip with a lower TDP than many competitors.

The PassMark physics score of 1553 and find prime numbers score of 98 are lower than expected, suggesting that the CPU's FPU performance is not its strongest suit. However, the floating point math score of 62629 and extended instructions score of 28474 show that the AVX-512 and other vector extensions are well-supported.

# FAQ

Q: What is the combined performance percentile of this CPU+GPU build?

A: The combined percentile is 87, which places the system in the upper tier of desktop builds. The CPU alone sits at the 82nd percentile, and the GPU at the 92nd percentile.

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

A: The GPU has 32 GB of GDDR7 memory on a 512-bit bus, providing 1.79 TB/s of bandwidth. This is sufficient for any current gaming or rendering workload.

Q: Is the Ryzen 7 8700F an unlocked processor?

A: Yes, the multiplier is unlocked, allowing for overclocking. The base clock is 4.10 GHz with a boost clock of 5.00 GHz, and the CPU has a 65W TDP.

Q: What socket and memory type does the CPU use?

A: The CPU uses AMD Socket AM5 and supports dual-channel DDR5 memory with 83.2 GB/s of bandwidth. ECC memory is not supported.

Q: What is the suggested power supply wattage for this GPU?

A: The suggested PSU for the RTX 5090 D is 950W, and the GPU draws 575W TDP. It requires a single 16-pin power connector.

Q: Does the CPU have integrated graphics?

A: No, the Ryzen 7 8700F has no integrated graphics (N/A). A discrete GPU is required for display output, which this build provides.

Q: What is the GPU's ray tracing and tensor core count?

A: The RTX 5090 D has 170 ray tracing cores and 680 tensor cores, supporting DirectX 12 Ultimate, Vulkan 1.4, and OpenGL 4.6.

# Usage Scenarios

High-Refresh Gaming: At 1440p, the system should deliver very high frame rates in competitive titles, given the GPU's 92nd percentile and CPU's 82nd percentile. The 3DMark Steel Nomad score of 14326 suggests that even demanding AAA games will run smoothly, though the CPU may cap frame rates in lighter esports titles.

Streaming: The 8-core/16-thread CPU provides enough headroom for game encoding while the GPU handles rendering. The PassMark multi-thread score of 30893 and 16-thread 3DMark score of 7883 indicate that the processor can manage streaming overhead without significant frame drops, and the GPU's tensor cores can assist with AI-driven encoding features.

Video Editing: The GPU's 32 GB VRAM and 1.79 TB/s bandwidth accelerate timeline scrubbing and effect rendering. The PassMark GPU compute score of 28396 and Geekbench OpenCL score of 310674 show strong compute performance for export tasks, while the CPU's Cinebench R23 multi-core score of 26646 handles encoding and project management.

3D Rendering: The RTX 5090 D's 104.8 TFLOPS FP32 and 21760 shading units provide immense rasterization and compute power. The CPU's 16 MB L3 cache and 16 threads may become a bottleneck in complex scenes, but the GPU's Vulkan score of 376915 indicates efficient multi-threaded command processing.

Software Development: The CPU's PassMark data compression score of 378160 and random string sorting score of 45425 support fast build times and code analysis. The single-thread score of 1008 in 3DMark ensures responsive IDE performance, while the GPU's compute capabilities enable local AI model testing.

Student and Office Work: The CPU's 65W TDP and efficient Zen 4 architecture make it a reasonable workstation processor. The PassMark multi-thread score of 30893 handles multitasking with ease, and the GPU's G2D score of 1487 ensures smooth 2D rendering for documents and spreadsheets, though this is overkill for most office tasks.

# Build Overview

This is a desktop build pairing the AMD Ryzen 7 8700F with the NVIDIA GeForce RTX 5090 D. The CPU is an 8-core/16-thread Zen 4 (Phoenix) processor on the AM5 socket, released in March 2024 with a launch MSRP of $270. The GPU is a Blackwell 2.0 architecture card based on the GB202 chip, released in January 2025 with a launch MSRP of 2,299 USD.

The system's combined percentile of 87 places it in the upper echelon of desktop builds, though the discrepancy between the CPU's 82nd percentile and GPU's 92nd percentile is notable. The CPU's nearest rivals are all within 1% in average benchmark score, indicating that the 8700F is a competent but not exceptional processor. The GPU's nearest rivals are mobile parts, which suggests the RTX 5090 D's full potential may not be captured by standard benchmarks.

The build is characterized by a powerful GPU that can handle any resolution and workload, paired with a capable but not class-leading CPU. This creates a system that excels in GPU-bound scenarios like 4K gaming and rendering, but may leave performance on the table in CPU-bound tasks. The AM5 platform offers a clear upgrade path for the processor, while the GPU's 32 GB VRAM and 1.79 TB/s bandwidth ensure it will remain relevant for years. This is a system for users who prioritize graphics performance above all else, with a processor that provides solid but not spectacular support.