SYSTEM ANALYZER

Rate My PC: AMD Ryzen AI Max PRO 390 + Intel Arc A380M

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
96%
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 PRO 390

63,765 Benchmark Score
Top 4% Market Ranking
View Full Specs →
GRAPHICS CARD

Intel Arc A380M

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 PRO 390 paired with the Intel Arc A380M is an unusual combination: a top-tier mobile processor from AMD's Zen 5-based Strix Halo family attached to an entry-level discrete GPU from Intel's Alchemist generation. The data makes the asymmetry plain. The CPU sits in the 93rd percentile against all tracked processors, while the GPU sits at exactly the 50th percentile against all tracked GPUs, and the pairing as a whole lands at the 72nd percentile. This is, in effect, a workstation-class compute engine strapped to a mainstream graphics solution — a build whose strengths and weaknesses follow directly from that split. One important caveat applies throughout: no measured frame-rate data exists for this exact combination, so all gaming discussion below is estimated from benchmark scores rather than measured results.

Usage Scenarios

High-refresh gaming. The Arc A380M is the limiting factor here. With 6 GB of GDDR6 on a 96-bit bus and 4.096 TFLOPS of FP32 throughput, the GPU's 50th-percentile position indicates middling graphics capability, and estimated frame rates at high settings will be modest at 1080p and below. The CPU's excellent single-thread scores (a 1976 Cinebench R23 single-core result and a 3967 PassMark single-thread score) mean the processor will almost never be the constraint — but a strong CPU cannot compensate for a mid-pack GPU. Expect competitive esports titles to be playable at high refresh rates with reduced settings, not ultra-settings triple-A gaming.

Streaming. Streaming is a CPU-bound overlay on gaming, and the 12-core, 24-thread Ryzen AI Max PRO 390 handles encoding and compositing comfortably — its PassMark multithread score of 42912 exceeds the average score of the Intel Core i9-13900KS by a small margin in the rival table (a 0.4 percent delta in AMD's favor on aggregate). The realistic constraint is the GPU's rendering headroom: if the game already taxes the A380M, adding a stream encode on the CPU side is fine, but the game itself will not get faster.

Video editing. This is one of the stronger scenarios for the pairing. The 64 MB of shared L3 cache, quad-channel LPDDR5X delivering 256 GB/s of memory bandwidth, and a Cinebench R23 multi-core score of 24828 put the CPU in genuinely capable territory for timeline scrubbing, multi-cam work, and export queues. The 6 GB of GPU VRAM is workable for 1080p editing and effects previews, though heavyweight GPU-accelerated effects stacks may press against that capacity.

3D rendering. CPU rendering is the story. The R23 multi-core score of 24828 and the R15 multi-core score of 3918 sit near an aggregate tier shared with the Intel Core i9-13900KS and the AMD EPYC 7343 — silicon ordinarily associated with sustained production work. GPU-path rendering, however, is bounded by the A380M's 8 ray-tracing cores and 4.096 TFLOPS FP32 figure, which relegates viewport interactivity and GPU render passes to entry-level expectations.

Software development. Compilation, containerization, and parallel test suites scale with cores and memory bandwidth, and the 24 threads plus 256 GB/s quad-channel bandwidth are strong assets here. The single-core result of 303 in Cinebench R15 keeps interactive tooling responsive. PassMark's integer math (148508) and floating point (94666) scores reinforce that this CPU handles branchy, scalar-heavy developer workloads as well as throughput-bound ones.

Student and office work. For documents, browsing, video calls, and coursework, this pairing is overkill on the CPU side and adequate on the GPU side. The integrated Radeon 8050S graphics already present on the die mean the discrete Arc A380M is largely redundant for this class of use, though it adds a modest margin for light creative applications.

Benchmark Performance

The CPU's benchmark sheet is deep and consistent. Cinebench R23 returns 24828 multi-core and 1976 single-core; Cinebench R15 returns 3918 multi-core and 303 single-core. PassMark reports 42912 multithread, 3967 single-thread, 148508 integer math, 94666 floating point math, 2773 physics, 506170 data compression, 26027 data encryption, 40888 extended instructions, 55248 string sorting, and 323 for prime number finding. The aggregate average benchmark score is 63765, placing the chip in the 93rd percentile of all tracked CPUs.

The rival table contextualizes that number tightly. The Intel Core i9-13900KS averages 64051 — just 0.4 percent ahead. The AMD EPYC 7343 averages 64202, 0.7 percent ahead. The AMD Ryzen AI 7 450G averages 63331, 0.7 percent behind, and the Intel Core Ultra 7 265HX averages 63173, 0.9 percent behind. In other words, this 55-watt mobile part trades blows with a flagship desktop i9 and a server EPYC on aggregate benchmark score — a striking efficiency statement.

The GPU side has no benchmark rows in the dataset. The Arc A380M carries a 50th-percentile placement against all GPUs — precisely median — and an average benchmark score of zero recorded, meaning its competitive position must be read from the percentile alone. The combined build percentile of 72 reflects the CPU dragging the median GPU upward: the pairing is materially stronger than the GPU alone would suggest.

FAQ

Q: How does the Ryzen AI Max PRO 390 compare to the Intel Core i9-13900KS?

A: On aggregate benchmark score, the two are nearly identical: 63765 for the AMD part versus 64051 for the i9-13900KS, a delta of just 0.4 percent in Intel's favor. The AMD chip achieves this at a 55 W TDP in a mobile package.

Q: Are there measured frame rates for this CPU and GPU combination?

A: No. The dataset contains no measured FPS entries for this pairing, so all gaming performance discussion is estimated from the benchmark scores and percentile positions rather than direct measurement.

Q: Is the CPU or the GPU the bottleneck for gaming?

A: The GPU. The CPU sits in the 93rd percentile of all processors while the Arc A380M sits at the 50th percentile of all GPUs. Nearly every graphically demanding scenario will be GPU-limited.

Q: How much memory bandwidth does the platform provide?

A: The CPU supports quad-channel LPDDR5X at 256 GB/s — bandwidth that benefits integrated graphics, data compression (506170 PassMark score), and memory-bound production workloads alike.

Q: Does the CPU support ECC memory?

A: Yes. ECC support is listed as true, which aligns the PRO designation with workstation and reliability-sensitive deployments.

Q: Is the multiplier unlocked for overclocking?

A: No. The multiplier is locked, consistent with a mobile, efficiency-focused platform on Socket FP11.

Q: What generation of PCIe does the CPU offer?

A: PCIe Gen 4 with 16 CPU lanes. The Arc A380M itself connects over an MXM-A (3.1) module interface rather than a standard desktop slot.

Who Should Build It

The natural owners of this configuration are professionals who need sustained multi-threaded compute in a mobile form factor without gaming as a priority. Developers compiling large codebases benefit directly from the 24 threads and the 42912 PassMark multithread result; data-handling roles benefit from the 506170 compression and 26027 encryption scores plus ECC support; small businesses running workstations for analysis, virtualization, or media encoding get desktop-i9-class aggregate performance (within 0.4 percent of the i9-13900KS) in a laptop-class envelope.

Content creators working at 1080p will find the CPU side excellent and the GPU side merely adequate — the 6 GB VRAM buffer is the practical ceiling for GPU-accelerated workflows. Gamers are the weakest fit unless the target is esports titles at 1080p or lower settings, where the A380M's median position is sufficient and the CPU's 3967 single-thread score guarantees no frame-time stutter from the processor side. Students in technical fields — engineering simulations, code, statistics — get a machine whose compute tier (93rd percentile CPU) far outlasts its graphics tier.

CPU Analysis

The Ryzen AI Max PRO 390 is a 12-core, 24-thread Zen 5 processor built on TSMC's 4 nm process, codenamed Strix Halo, on Socket FP11. It clocks from a 3.20 GHz base to a 5.00 GHz boost. The cache hierarchy is generous: 80 KB of L1 per core, 1 MB of L2 per core, and 64 MB of shared L3 — the large shared pool being a significant contributor to the chip's strong multi-core scaling in rendering tests.

The benchmark profile shows a balanced design rather than a throughput-specialized one. The single-core R23 score of 1976 and single-thread PassMark score of 3967 indicate top-tier per-core responsiveness, which matters for game logic, toolchains, and application launch behavior. Meanwhile the multi-core results — 24828 in R23, 3918 in R15, 42912 in PassMark multithread — place aggregate throughput beside the Core i9-13900KS (0.4 percent delta) and the EPYC 7343 (0.7 percent delta), both of which are desktop/server parts with far higher power envelopes than this chip's 55 W TDP. The PassMark physics score of 2773 and floating point score of 94666 reinforce that simulation and numeric workloads are well served.

The quad-channel LPDDR5X controller delivering 256 GB/s is arguably the platform's defining feature — it feeds the 64 MB L3 quickly and provides the memory bandwidth that memory-bound workloads (the 506170 compression result is a good proxy) demand. Note the PRO suffix and ECC support: this silicon is aimed at managed fleets and reliability-conscious buyers, and the locked multiplier confirms it is not an enthusiast tuning part.

Gaming Performance

No measured FPS data exists for this exact CPU and GPU combination — every figure in this section is an estimate derived from benchmark scores, not measurement.

The estimate framework is straightforward. The Arc A380M's 50th-percentile GPU position, 1024 shading units, 4.096 TFLOPS FP32, and 186 GB/s of memory bandwidth describe an entry-level discrete solution. At 1080p with ultra settings, modern graphically demanding titles should be expected to run at frame rates that are playable rather than high; the 6 GB VRAM buffer is the binding constraint at ultra texture quality. Reducing settings or resolution should scale frame rates meaningfully, as the CPU side presents no ceiling — the 3967 single-thread score sits in the 93rd-percentile CPU's portfolio and will feed frames as fast as the GPU can consume them.

At 1440p and 4K, the A380M's 64 GPixel/s pixel rate and 96-bit bus make ultra-settings play unrealistic for current triple-A releases; lighter or older engines and esports titles are the realistic diet. Ray tracing is technically available via the 8 RT cores and DirectX 12 Ultimate support, but enabling it on a median-percentile GPU will cost a large fraction of performance and is best treated as a demonstration feature rather than a daily setting. The Vulkan 1.4 and OpenGL 4.6 API coverage means compatibility is broad even where speed is limited.

Balance and Bottleneck

The bottleneck analysis is unusually one-sided. The CPU occupies the 93rd percentile of all processors; the GPU occupies the 50th percentile of all GPUs. A greater than 40-percentile gap between components defines this build: virtually every graphically intensive workload will run into the GPU ceiling long before the CPU shows strain.

The evidence is in the scaling logic rather than measured FPS — none exists — but the CPU's headroom is unambiguous. With a PassMark multithread score of 42912 and single-thread score of 3967, the processor can drive far stronger graphics hardware without becoming the limiter; the rival comparison to the i9-13900KS makes clear that frame delivery from the CPU side is flagship-grade. Conversely, there is no realistic workload in which the Arc A380M underutilizes this CPU in gaming — the GPU saturates first by a wide margin.

For non-gaming workloads the picture inverts pleasantly: rendering, compression, encryption, and compilation are CPU-bound and the GPU simply idles. The integrated Radeon 8050S on the CPU die further complicates the discrete GPU's role — for display output and light work, the A380M adds only marginal capability over the integrated solution. The combined 72nd percentile honestly reflects a strong compute platform with median graphics attached.

Build Overview

This is a laptop-class build: a mobile Ryzen AI Max PRO 390 (Socket FP11, 55 W TDP, market segment Mobile, production status Active) paired with an MXM-module Intel Arc A380M (35 W TDP). The pairing is asymmetric by design or by fleet configuration — a workstation processor with an entry-level discrete GPU, where the integrated Radeon 8050S already covers baseline display duties.

By tier, the CPU alone is 93rd percentile, the GPU alone is 50th percentile, and the combination registers 72nd percentile overall. That composite number is the honest summary: this machine ranks well above the median tracked system in aggregate capability, but that standing is carried almost entirely by the processor. Anyone evaluating this configuration on its combined percentile should understand what the number conceals — top-decile compute with median-decile graphics.

Upgrade Path and Platform

The platform fundamentals are dictated by Socket FP11, a soldered mobile package — meaning the CPU itself is not user-replaceable in the conventional sense. Memory support is LPDDR5X over a quad-channel bus at 256 GB/s with ECC available; memory configuration is effectively fixed at system build time on this platform class. PCIe is Gen 4 with 16 CPU lanes, enough for a single graphics device at full width or a mix of storage and accelerators in a desktop-style deployment.

Power headroom is modest and defined: a 55 W CPU TDP plus a 35 W GPU TDP gives a combined 90 W of component budget, and the MXM module requires no separate power connectors — the board's delivery design handles both. No suggested PSU figure is provided for the GPU, consistent with its MXM mobile form factor where power provisioning is platform-integrated.

The sensible next upgrade is therefore on the graphics side. Because the CPU's 93rd-percentile benchmark profile and flagship-adjacent aggregate score leave enormous graphics headroom untapped, moving to a substantially stronger GPU — one that shifts the system's graphics percentile upward toward the CPU's — would rebalance the build without wasting the processor. Storage and peripheral expansion via the Gen 4 lanes, plus ECC-capable memory configurations where the platform allows, round out the realistic growth paths.

GPU Analysis

The Intel Arc A380M is an Alchemist-generation Xe-HPG part, the DG2-128 die fabricated on TSMC's 6 nm process. The die measures 157 mm² and packs 7200 million transistors for a density of 45.9 million per square millimeter. It carries 1024 shading units, 64 texture mapping units, 32 render output units, and 8 ray-tracing cores; no tensor cores are listed in the dataset.

Clocks run from a 1550 MHz base to a 2000 MHz boost, with memory clocked at 1937 MHz (15.5 Gbps effective). The memory subsystem is the clearest indicator of the card's class: 6 GB of GDDR6 across a 96-bit bus yields 186 GB/s of bandwidth — a fraction of the 256 GB/s the host CPU's own quad-channel controller provides, and a structural limit at higher resolutions and texture settings. Throughput figures follow: 64 GPixel/s pixel rate, 128 GTexel/s texture rate, 4.096 TFLOPS FP32, and 8.192 TFLOPS FP16 at a 2:1 ratio. The FP16 capability gives it some standing in half-precision inference and effects work, though the absence of listed tensor hardware tempers any AI-workload ambitions.

Feature support is modern on paper: DirectX 12 Ultimate (12_2), Vulkan 1.4, and OpenGL 4.6, with 8 RT cores enabling hardware ray tracing. What the feature list promises, the percentile placement contextualizes — at the 50th percentile among all tracked GPUs, the A380M delivers exactly median rendering capability. For this build, that means the GPU defines the gaming and GPU-rendering ceiling while the 93rd-percentile CPU defines everything else. As a pairing, it is a compute platform with competent, unremarkable graphics bolted on.