SYSTEM ANALYZER

Rate My PC: AMD Ryzen AI Max 390 + AMD Radeon 840M

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

85 / 100
HIGH-END

Power Build

Top 15% of systems. Excellent for 1440p Ultra or 4K High gaming.

1440p Ultra4K High

System Balance Analysis

CPU vs GPU performance ratio
GPU Bottleneck
CPU
95%
VS
GPU
74%

Your GPU is limiting system performance. Consider upgrading to a more powerful graphics card to better utilize your CPU.

PROCESSOR

AMD Ryzen AI Max 390

56,273 Benchmark Score
Top 5% Market Ranking
View Full Specs →
GRAPHICS CARD

AMD Radeon 840M

0 Benchmark Score
Top 26% 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

Strong Performance

Excellent for 1440p gaming. Most games will run at high/ultra settings smoothly.

Bottleneck Detected

GPU Bottleneck - Upgrading the weaker component will improve overall performance.

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

The AMD Ryzen AI Max 390 pairs a 12-core Zen 5 processor with the Radeon 840M integrated GPU in a laptop build, targeting the 91st percentile among all CPUs but only the 50th percentile among GPUs. This combination produces a system with substantial processing power for professional and creative workloads, while graphics performance remains firmly in the mainstream tier for gaming and GPU-accelerated tasks. The data shows a clear split: the CPU is a high-end mobile powerhouse, while the GPU is an entry-level integrated solution, making the overall system's 71st combined percentile a reflection of its processor-led character.

FAQ

Q: What kind of processor is the AMD Ryzen AI Max 390?

A: It is a mobile CPU from AMD's Ryzen AI Max generation, built on the Zen 5 architecture with the codename Strix Halo. It has 12 cores and 24 threads, manufactured on a 4 nm process by TSMC, and is designed for laptops using the AMD Socket FP11.

Q: How fast is the CPU in multi-threaded workloads compared to its nearest rivals?

A: In the Cinebench R23 multi-core test, the Ryzen AI Max 390 scores 36,064 points. Its average benchmark score of 56,273 is virtually identical to the AMD Ryzen AI 9 HX PRO 470, which scores 56,306, differing by only -0.1%. It is also 0.5% ahead of the Intel Core i9-14900HX and 0.6% ahead of the Intel Core 7 253PQE.

Q: What are the clock speeds and cache specifications of this CPU?

A: The CPU has a base clock of 3.20 GHz and a boost clock of 5.00 GHz. It features 80 KB of L1 cache per core, 1 MB of L2 cache per core, and a shared 64 MB L3 cache, with the processor's total power draw rated at 55 W.

Q: What graphics solution is integrated into this system?

A: The build includes the AMD Radeon 840M, an integrated GPU based on the RDNA 3.5 architecture with the chip codename Krackan Point. It operates with a base clock of 400 MHz and a boost clock of 2900 MHz, and it uses system-shared memory.

Q: How does the Radeon 840M's performance compare to other GPUs?

A: The Radeon 840M sits at the 50th percentile among all GPUs, indicating it is exactly in the middle of the performance range. Its average benchmark score is listed as 0 in the data, and it has no nearest rivals listed, which suggests limited comparative data is available for this specific IGP.

Q: What is the memory configuration for this laptop build?

A: The system supports LPDDR5X memory with a quad-channel bus, providing a total memory bandwidth of 256.0 GB/s. The CPU also supports ECC memory, a feature typically associated with workstations and servers.

Q: Is there measured gaming frame rate data for this specific CPU and GPU combination?

A: No, the data pack contains no measured FPS rows for this exact pairing. All gaming performance discussion must therefore be treated as an estimate derived from the individual benchmark scores of the CPU and GPU, rather than from direct testing.

Benchmark Performance

The benchmark data paints a clear picture of a system with a dominant CPU and a modest GPU. The Ryzen AI Max 390's CPU performance is exceptional, placing it in the 91st percentile of all processors, with an average benchmark score of 56,273. This score puts it in a dead heat with the AMD Ryzen AI 9 HX PRO 470, which is only 0.1% faster, and slightly ahead of both the Intel Core i9-14900HX and Intel Core 7 253PQE, which it beats by 0.5% and 0.6%, respectively. This near-tie with a high-end Intel HX-series chip underscores the Ryzen's capability in mobile form factors.

In multi-threaded tests, the CPU demonstrates its strength. The Cinebench R23 multi-core score of 36,064 points is a strong indicator of heavy parallel processing capability, while the R20 and R15 scores of 15,146 and 3,635 points, respectively, show consistent scaling across benchmark generations. Single-thread performance is also robust, with a Cinebench R23 single-core score of 5,091 points and a PassMark single-thread score of 4,028, indicating strong responsiveness in everyday tasks and lightly-threaded applications.

The PassMark suite reveals a processor that excels in specific computational tasks. The multithread score of 41,737 points is notable, but the real standout is the data compression score of 487,145, which is an outlier figure suggesting exceptional throughput in that specific workload. Integer math performance is also strong at 146,519 points, and floating-point math reaches 90,594 points. The data encryption score of 25,097 points and extended instructions score of 38,716 points round out a profile that is well-suited for both scientific computing and secure data handling.

On the graphics side, the Radeon 840M presents a stark contrast. With a 50th percentile ranking among all GPUs and an average benchmark score of 0, it is a truly mainstream component. Its FP32 performance of 1,484.8 GFLOPS is a baseline figure for integrated graphics. The combined picture is of a system that can handle professional-level computational tasks with ease but will be the limiting factor in any graphics-intensive scenario. The overall combined percentile of 71 reflects this imbalance, pulled down by the GPU's middling position despite the CPU's top-tier ranking.

Balance and Bottleneck

The performance data indicates a significant imbalance between the CPU and GPU, making the Radeon 840M the clear bottleneck in graphics-intensive workloads. The CPU's 91st percentile ranking against all CPUs places it among the top 10% of processors, while the GPU's 50th percentile ranking places it squarely in the middle of the GPU pack. This means that in any application that relies heavily on GPU compute or rendering, the CPU will be waiting on the GPU to finish its work, severely limiting the system's overall throughput.

This bottleneck is most evident in gaming scenarios. The CPU's single-thread score of 5,091 in Cinebench R23 suggests it can feed frames to the GPU at a high rate, but the Radeon 840M's modest FP32 compute of 1,484.8 GFLOPS will cap the frame rate well before the CPU becomes a limitation. In CPU-bound scenarios, such as physics calculations or AI logic, the processor will be the dominant force, but with the GPU handling the graphics rendering, the system's overall performance is tethered to the graphics solution's capabilities.

For productivity tasks, the balance shifts back toward the CPU. Video encoding, software compilation, and data processing are typically CPU-bound, and here the Ryzen AI Max 390's 12 cores and 24 threads will be fully utilized. The data shows the CPU is a top-tier mobile part that can compete with desktop-class processors like the Threadripper PRO 3955WX, which it trails by only 0.5%. The bottleneck in these workloads is less about hardware balance and more about memory bandwidth or storage speed, which are not directly measured in the data. The system's 256.0 GB/s memory bandwidth is a strong figure for an integrated platform, suggesting it can feed the CPU's cores adequately in multi-threaded tasks.

The FPS scaling evidence, while not measured directly, can be inferred from the benchmark scores. A GPU that scores at the 50th percentile will produce playable but not high-refresh results at lower resolutions, while the CPU's high percentile ensures it will not be the cause of frame drops in most scenarios. The bottleneck is therefore clear: the Radeon 840M is the limiting factor for gaming, and the Ryzen AI Max 390 is the limiting factor for GPU-accelerated compute tasks, though its high performance means it is a less restrictive bottleneck than the GPU is for games.

Who Should Build It

This laptop build is tailored for users who prioritize raw CPU processing power over graphics performance. The 91st percentile CPU ranking makes it an excellent choice for professionals who work with heavily multi-threaded applications. Content creators, such as video editors and 3D modelers, will benefit from the 12 cores and 24 threads when rendering or exporting, though they may need to rely on CPU-based rendering rather than GPU acceleration for final output. Software developers and data scientists will find the high integer math score of 146,519 and data compression score of 487,145 particularly useful for compiling code and handling large datasets.

Students in engineering or scientific fields can leverage the CPU's floating-point performance of 90,594 and the extended instructions score of 38,716 for simulation and analysis software. The system's ECC memory support is a significant feature for those working on financial models or scientific research where data integrity is critical. Small business workstations that run complex spreadsheets, databases, or virtual machines will find the multithread score of 41,737 and the 24 threads more than adequate for their needs.

However, gamers and graphics professionals should look elsewhere or pair this CPU with a discrete GPU. The Radeon 840M's 50th percentile ranking means it is not suitable for high-end gaming or GPU-accelerated rendering. The system is built for a user who needs a powerful mobile workstation for CPU-intensive tasks and is willing to accept integrated graphics as a secondary feature. For a user who wants a single machine for both heavy processing and gaming, this build would be frustrating, as the CPU's potential would be wasted by the GPU's limitations.

Usage Scenarios

High-Refresh Gaming: This is not a suitable system for high-refresh gaming. The Radeon 840M's 50th percentile GPU ranking and FP32 performance of 1,484.8 GFLOPS will struggle to push high frame rates at any resolution above 1080p with modern titles. The CPU's 5,091 single-core score in Cinebench R23 is more than sufficient, but the GPU is the definitive bottleneck, making high-refresh gaming unattainable with this integrated graphics solution.

Streaming: The CPU is well-equipped for streaming tasks. The 12 cores and 24 threads provide ample headroom for encoding video while running a game, and the data encryption score of 25,097 suggests the hardware can handle the encoding overhead. However, the game itself will run on the weak GPU, so streaming would be limited to less demanding titles or lower graphical settings. The CPU is a streaming workhorse, but the GPU drags the overall experience down.

Video Editing: This is a strong scenario for the CPU. The high multi-core scores, including 36,064 in Cinebench R23, will make short work of video exports and timeline scrubbing in editing software. The 64 MB of L3 cache helps with large media files, and the 256.0 GB/s memory bandwidth supports smooth playback of high-resolution footage. The GPU is not powerful enough for demanding effects or GPU-accelerated rendering, but the CPU alone can handle most editing workflows.

3D Rendering: CPU-based rendering will be excellent, with the 24 threads providing substantial parallel processing power. The PassMark multithread score of 41,737 and the floating-point math score of 90,594 indicate strong performance in physics simulations and ray tracing calculations. GPU-accelerated rendering is not viable with the Radeon 840M, so users must rely on CPU-based engines, which will still be fast but not as quick as a dedicated graphics card.

Software Development: This is an ideal scenario for the CPU. Compilation times will be short thanks to the high integer math score of 146,519 and the 24 threads. The large 64 MB L3 cache helps with repeated code compilation, and the data compression score of 487,145 suggests fast archive extraction and handling of large codebases. The GPU is irrelevant for most development tasks, making this a near-perfect build for a programmer.

Student and Office Work: This build is overkill for basic office tasks, but the performance headroom ensures smooth multitasking. The 4,028 PassMark single-thread score guarantees snappy responsiveness in word processors and web browsers, while the 24 threads handle background tasks without any slowdown. The ECC memory support is a bonus for students in technical fields who need reliable long-running calculations. The GPU is sufficient for light media consumption and standard office graphics.

Gaming Performance

There is no measured FPS data for this exact CPU and GPU combination. All gaming performance figures discussed here are estimates based on the individual benchmark scores of the components and should be treated as such. The Radeon 840M's 50th percentile standing among all GPUs suggests it performs at the median level for graphics cards, which in practice means it is suitable for esports titles and older games at 1080p with medium to low settings.

The CPU's high single-thread performance of 5,091 in Cinebench R23 ensures that it will not be a bottleneck in most gaming scenarios, allowing the GPU to operate at its full potential. For a game like "Counter-Strike 2" or "Valorant," which are CPU-bound and not graphically demanding, the system might achieve playable frame rates above 60 FPS at 1080p with low settings, given the GPU's 256 shading units and 8 ROPs. However, for modern AAA titles like "Cyberpunk 2077" or "Starfield," the GPU's 1,484.8 GFLOPS of FP32 performance is too low to maintain smooth frame rates, likely resulting in sub-30 FPS experiences even at the lowest settings.

The lack of measured data means these estimates rely on the GPU's architecture and specs. The RDNA 3.5 architecture with 4 RT cores suggests some ray tracing capability, but the 50th percentile ranking indicates it is not a strong performer in this area. The GPU's 16 TMUs and 8 ROPs are low numbers, which will limit texture fill rate and pixel throughput. In summary, the system is not designed for serious gaming, and users should expect it to handle only light or older titles.

CPU Analysis

The AMD Ryzen AI Max 390 is a 12-core, 24-thread processor based on the Zen 5 architecture, built on a 4 nm process by TSMC. Its die size is listed as 2x 70.6 mm², indicating a chiplet design, and it uses the AMD Socket FP11. The CPU's base clock of 3.20 GHz and boost clock of 5.00 GHz are typical for a high-end mobile processor, and its 55 W TDP is a modest figure for the performance it delivers. The cache hierarchy is substantial, with 80 KB of L1 per core, 1 MB of L2 per core, and a large 64 MB shared L3 cache, which is critical for keeping all 12 cores fed with data.

Benchmark results show this CPU is a top-tier mobile part. The Cinebench R23 multi-core score of 36,064 points places it in the 91st percentile of all CPUs, and its average score of 56,273 is competitive with the Intel Core i9-14900HX, which it beats by 0.5%. The PassMark multithread score of 41,737 points is particularly strong, indicating excellent performance in heavily threaded applications. The single-thread score of 4,028 in PassMark and 5,091 in Cinebench R23 show strong per-core performance, which is essential for daily tasks and legacy applications that don't use many threads.

The CPU's memory support for LPDDR5X with a quad-channel bus and 256.0 GB/s bandwidth is a key differentiator. This high bandwidth is crucial for an integrated platform where the GPU shares system memory, and it also benefits CPU-bound workloads like data compression, which achieved a score of 487,145 in PassMark. The ECC memory support is a professional feature that adds reliability for long-running computations. The architecture is Zen 5, which is AMD's latest, and the "Strix Halo" codename suggests this is a flagship mobile processor. The data shows a CPU that can handle anything from software compilation to scientific simulation with ease.

Build Overview

This is a laptop build that pairs the AMD Ryzen AI Max 390 CPU with the AMD Radeon 840M integrated GPU. The combination results in a system that sits at the 71st combined percentile, which reflects the CPU's high performance (91st percentile) and the GPU's average performance (50th percentile). The CPU is a 12-core Zen 5 part designed for mobile workstations, while the GPU is an RDNA 3.5 integrated solution with 256 shading units. The build class is explicitly defined as "laptop," making it a portable workstation rather than a desktop substitute.

The overall tier of this build is that of a professional workstation with a significant gaming deficiency. The CPU's benchmark scores are in the same league as desktop workstation processors like the AMD Ryzen Threadripper PRO 3955WX, which it trails by only 0.5%. This makes the system a legitimate choice for CPU-intensive professional work. The GPU, however, is only at the 50th percentile, meaning it is an average performer for integrated graphics but well below what a discrete GPU would offer. The build is a study in contrasts: a top-10% processor paired with a 50th-percentile graphics solution. For users who need the CPU power and can tolerate the GPU limitations, it is a compelling package; for those who need balanced performance, it is a mismatch.

GPU Analysis

The AMD Radeon 840M is an integrated GPU based on the RDNA 3.5 architecture with the chip codename Krackan Point. It is manufactured on a 4 nm process by TSMC and features 256 shading units, 16 texture mapping units, and 8 ROPs. The GPU operates at a base clock of 400 MHz and a boost clock of 2900 MHz, with a TDP of 15 W. It has 4 RT cores for ray tracing, but no tensor cores are listed. Memory is system-shared, meaning it uses a portion of the main system RAM, with a bus width and bandwidth that are system-dependent.

In terms of performance, the Radeon 840M sits at the 50th percentile among all GPUs, indicating it is an average performer. Its FP32 compute is 1,484.8 GFLOPS, and its FP16 performance is identical at 1,484.8 GFLOPS, suggesting no dedicated tensor acceleration. The pixel rate is 23.20 GPixel/s and the texture rate is 46.40 GTexel/s, both of which are modest figures. The GPU supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, ensuring compatibility with modern APIs, but its raw performance is limited.

For rendering tasks, this GPU is a weak link. The 8 ROPs are a significant limiting factor for pixel fill rate, which will impact high-resolution rendering. The 4 RT cores provide some ray tracing capability, but the low overall compute means ray-traced effects will be extremely slow. The system-dependent memory bandwidth, while not specified, is shared with the CPU, and the CPU's 256.0 GB/s LPDDR5X bandwidth is a high figure that should help the GPU somewhat. However, the GPU's 50th percentile ranking and lack of measured benchmark scores indicate it is not designed for serious graphics work, serving instead as a basic display output for the powerful CPU.