SYSTEM ANALYZER

Rate My PC: AMD Ryzen AI Max PRO 390 + AMD Radeon 780M

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

Build Configuration

Select your components

PROCESSOR (CPU)

▼

GRAPHICS CARD (GPU)

▼

93 Score

Top 7% Ranking

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

96%

GPU

90%

PROCESSOR

AMD Ryzen AI Max PRO 390

63,765 Benchmark Score

Top 4% Market Ranking

View Full Specs →

GRAPHICS CARD

AMD Radeon 780M

17,588 Benchmark Score

Top 10% 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

The AMD Ryzen AI Max PRO 390 paired with the AMD Radeon 780M is a laptop-class combination defined by a stark asymmetry: a processor sitting in the 93rd percentile of all CPUs attached to an integrated GPU in the 61st percentile. The combined percentile of 77 reflects a build whose compute muscle vastly outruns its graphics capability, and whose 12 Zen 5 cores and 24 threads make it far closer to a mobile workstation than a gaming rig. This page walks through the recorded benchmark data step by step, and one caveat applies throughout: no measured FPS rows exist for this exact pairing in the database, so all gaming frame-rate discussion below is estimated from the benchmark scores rather than directly measured.

CPU Analysis

The Ryzen AI Max PRO 390 is a Zen 5 processor built on TSMC's 4 nm process under the Strix Halo codename, with 12 cores and 24 threads operating at a 3.20 GHz base and a 5.00 GHz boost clock. The cache hierarchy is generous for a mobile part: 80 KB of L1 and 1 MB of L2 per core, backed by a large shared 64 MB L3 pool. That L3 capacity matters for both gaming latency and content-creation workloads where large working sets would otherwise spill to system memory.

Memory support is LPDDR5X over a quad-channel bus, delivering 256.0 GB/s of bandwidth — a figure that is unusually high for the mobile segment and directly benefits the integrated graphics discussed later. ECC memory is supported, which is a hallmark of the PRO branding and relevant for professional stability requirements. The processor interfaces with the platform through AMD Socket FP11 and provides PCIe Gen 4 with 16 lanes from the CPU. Its stated TDP is 55 W, its multiplier is locked, and its market segment is listed as Mobile with an Active production status and a release date of 2025-01-05.

The benchmark numbers describe a genuinely strong all-rounder. In Cinebench R23 the chip posts 24828 in multi-core and 1976 in single-core; in the older R15 test it records 3918 multi-core and 303 single-core. A single-core score near two thousand in R23 indicates snappy per-thread responsiveness — application launches, browser tabs, and lightly threaded tools all behave like a modern desktop-class CPU rather than a power-sipping notebook part. The multi-core result, multiplied across 24 threads, indicates sustained throughput suitable for compilation, rendering, and simulation workloads. PassMark reinforces this: 42912 in the multithread test against 3967 single-thread, plus 148508 integer math, 94666 floating point math, 506170 data compression, and 26027 data encryption scores. The find-prime-numbers result of 323 and physics score of 2773 round out a profile that is compute-dense across integer, floating-point, and memory-sensitive tests. For real workloads, this means fast video encodes, quick code builds, and comfortable multitasking headroom — the data shows a processor that is rarely the limiting factor in any software task.

Benchmark Performance

The CPU's average benchmark score is 63765, placing it in the 93rd percentile versus all CPUs in the database. Context comes from the nearest rivals: the Intel Core i9-13900KS averages 64051 (the 390 sits 0.4 percent below it), the AMD EPYC 7343 averages 64202 (0.7 percent above), the AMD Ryzen AI 7 450G averages 63331 (0.7 percent below the 390), and the Intel Core Ultra 7 265HX averages 63173 (0.9 percent below). Landing within one percent of a desktop-flagship-tier i9 and a server EPYC part is the headline: this mobile processor trades blows with silicon from classes above its own segment.

The GPU side is more modest. The Radeon 780M's average benchmark score is 17588, in the 61st percentile versus all GPUs. Its rivals are the AMD Radeon Pro 560 at 17551 (0.2 percent below the 780M), the NVIDIA GeForce RTX 4060 at 17639 (0.3 percent above), the AMD Radeon HD 7790 at 17666 (0.4 percent above), and the AMD Radeon Pro 460 at 17509 (0.5 percent below). Note that percentile and average-score methods measure different populations, so a 61st-percentile integrated GPU can sit numerically near those named dGPU rivals in this dataset's composite metric — the practical reading is that the 780M is a strong integrated solution but not a discrete-class gaming engine.

The GPU's individual benchmark results are a 3DMark Steel Nomad DX12 score of 480, Geekbench OpenCL at 18602, and Geekbench Vulkan at 33683. The Vulkan result being roughly 1.8 times the OpenCL result indicates the graphics driver stack performs markedly better under Vulkan APIs, which is worth remembering for game and compute-library selection. The combined percentile of 77 for the pairing captures the overall picture: an elite CPU dragging a mid-pack GPU upward, with the CPU unquestionably the stronger half.

Usage Scenarios

High-refresh gaming. No measured FPS data exists for this pairing, so expectations must be inferred from the scores. A Steel Nomad score of 480 and a 61st-percentile GPU indicate that high-refresh, ultra-settings play at 1080p in demanding titles is beyond this configuration's realistic envelope; lighter or older titles are where high frame rates become plausible. CPU headroom is never the issue — the 390's 93rd percentile means the processor will not be the reason frames drop.

Streaming. Encoding a stream while gaming splits the load between CPU and GPU, and here the 12-core/24-thread CPU with a 24828 Cinebench R23 multi-core score comfortably absorbs the encoding overhead. The constraint is the GPU's rendering capacity: the same modest graphics benchmark scores mean the game itself must run at reduced settings to hold frame rates while streaming.

Video editing. This is a strength. The CPU's floating-point score of 94666, integer score of 148508, and data-compression result of 506170 all support timeline scrubbing, encoding, and export throughput, while the 256.0 GB/s of quad-channel LPDDR5X bandwidth keeps large video assets moving. GPU-accelerated effects are handled by the 780M's 8.909 TFLOPS of FP32, which is adequate for playback acceleration but will not rival discrete solutions for final-render GPU effects.

3D rendering. CPU-based rendering is excellent — 24828 in Cinebench R23 multi-core and proximity to the EPYC 7343 on average score mean viewport interaction and CPU final renders are quick. GPU-path rendering (OpenCL/Vulkan) is usable given the 18602 OpenCL and 33683 Vulkan Geekbench scores, but the 480 Steel Nomad result signals that heavy real-time 3D scenes will require setting reductions.

Software development. Arguably the best-fit scenario. Compilation is throughput-bound, and a 42912 PassMark multithread score with 24 threads translates directly into fast parallel builds; the 3967 single-thread score keeps IDEs and debuggers responsive. ECC support adds correctness assurance for long-running test and build infrastructure.

Student and office work. Overkill in the best sense. Single-core scores of 1976 (R23) and 303 (R15) mean documents, browsers, and conferencing software feel instant, and the 64 MB of shared L3 keeps many-app multitasking smooth. Battery-conscious graphics switching to integrated silicon is inherent to this laptop-class design.

FAQ

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

A: The database places the 390 just 0.4 percent below the i9-13900KS on average benchmark score (63765 vs 64051) — remarkable for a mobile-class, 55 W TDP processor.

Q: Can the Radeon 780M handle modern games at high settings?

A: The evidence says only partially. With a 61st percentile ranking, a Steel Nomad score of 480, and an average score within half a percent of the Radeon Pro 560 and Pro 460, expectations should be moderate settings at reduced resolutions for demanding titles.

Q: How much memory bandwidth does this platform have?

A: 256.0 GB/s, thanks to quad-channel LPDDR5X support — bandwidth the integrated graphics draw on directly, since the 780M uses system-shared memory.

Q: Is the CPU good for multi-threaded workloads like rendering or compiling?

A: Yes. With 12 cores, 24 threads, a Cinebench R23 multi-core score of 24828, and a PassMark multithread result of 42912, the data places it in the 93rd percentile of all CPUs.

Q: Are measured gaming frame rates available for this pairing?

A: No. The database contains no measured FPS rows for this exact combination, so all frame-rate discussion on this page is estimated from benchmark scores.

Q: Does the platform support ECC memory?

A: Yes, ECC is supported on the Ryzen AI Max PRO 390, consistent with its PRO positioning for professional use.

Q: Which graphics API performs better on the 780M?

A: Vulkan clearly. The Geekbench Vulkan score of 33683 is substantially higher than the OpenCL score of 18602, indicating better performance through Vulkan-based paths.

Balance and Bottleneck

This pairing is GPU-bottlenecked in nearly every graphics workload, and the percentiles make that unambiguous. The CPU sits at the 93rd percentile; the GPU at the 61st. In any game or GPU-rendering task, the Radeon 780M finishes its work queue long after the Ryzen AI Max PRO 390 has gone idle — the processor's PassMark physics score of 2773 and single-thread score of 3967 mean simulation and draw-call submission will never be the limiting stage, while the 480 Steel Nomad result shows the rendering stage is the choke point.

Because no measured FPS rows exist for this combination, scaling must be reasoned from the scores rather than observed: dropping resolution and settings shifts load toward the CPU, where enormous headroom exists, so frame-rate gains from lowering graphics quality should be substantial and sustained. Conversely, raising resolution or enabling ray tracing — with only 12 RT cores on the 780M — will hit the GPU's ceiling quickly, and no amount of CPU throughput can compensate. For compute workloads the balance inverts: OpenCL and Vulkan compute tasks run on the GPU are the slow half, and CPU-native compute is the fast half. The quad-channel 256.0 GB/s memory bus is the one shared resource that helps the GPU punch above its nominal class, since system-shared VRAM lives and dies by memory bandwidth.

Who Should Build It

The data points to professional mobile users first. Software developers get a 24-thread, 93rd-percentile CPU with ECC support and PCIe Gen 4 storage lanes — an excellent portable build machine. Content creators doing video editing and CPU-based 3D rendering benefit from the 24828 R23 multi-core score and 256.0 GB/s of bandwidth, provided they accept that GPU-accelerated rendering tops out at integrated-class throughput. Small-business workstation users — CAD-lite, financial modeling, data analysis — get EPYC-adjacent CPU performance in a laptop chassis, with the PRO/ECC combination supporting reliability-sensitive deployments. Students and general office users are served exceptionally well but may never touch the processor's ceiling. The one audience to caution is the high-refresh gamer: with the GPU within a few tenths of a percent of the Radeon Pro 560 and Pro 460 on average score, this is a casual-graphics build, not an enthusiast gaming platform, and those seeking high-detail or high-resolution play at high frame rates should look toward the 780M's stronger rivals such as the RTX 4060 on the database's average-score metric.

GPU Analysis

The Radeon 780M is a Phoenix-based integrated GPU on the RDNA 3.0 architecture, manufactured by TSMC on a 4 nm node. The die measures 178 mm² and packs 25,390 million transistors at a density of 142.6 million per square millimeter. It runs at an 800 MHz base and 2900 MHz boost clock, with memory clocks tied to system-shared memory. The shader array comprises 768 shading units, 48 texture mapping units, 32 render outputs, and 12 ray-tracing cores. Peak rates are 92.80 GPixel/s pixel fill, 139.2 GTexel/s texture fill, and 8.909 TFLOPS of FP32 — with FP16 at the same 8.909 TFLOPS in a 1:1 configuration. The bus interface is PCIe 4.0 x8, the slot is an IGP with no power connectors, TDP is listed at 15 W, and API support extends to DirectX 12 Ultimate (feature level 12_2), OpenGL 4.6, and Vulkan 1.4.

For rendering, the practical reading is straightforward. The 8.909 TFLOPS FP32 figure and 33683 Vulkan Geekbench score handle viewport work and GPU compute respectfully for an integrated part, while the 480 Steel Nomad DX12 score defines the real-time rendering ceiling: modern engine loads must be trimmed in resolution or settings to run smoothly. The 12 RT cores enable hardware ray tracing on paper, but the fill-rate and shading budgets mean RT effects will exact a heavy toll. The 1:1 FP16 rate is relevant for inferencing-style workloads, though the absence of dedicated tensor cores means AI acceleration is general-purpose rather than fixed-function. Because memory is system-shared, the 256.0 GB/s quad-channel bandwidth of the host platform is effectively the GPU's memory bandwidth — the single biggest architectural advantage this configuration has over typical single-channel integrated graphics setups.

Build Overview

This is a laptop-class build, as recorded in the buildClass field: a mobile workstation pairing, not a desktop tower. Its identity is the AMD Ryzen AI Max PRO 390 (Zen 5, Strix Halo, 12C/24T, 55 W TDP, FP11 socket) combined with the AMD Radeon 780M integrated GPU (RDNA 3.0, Phoenix, 15 W). Notably, the CPU's own listed integrated graphics is the Radeon 8050S, so the 780M pairing as catalogued here represents the graphics configuration driving this system's measured scores. By tier, the data is clear: a 93rd-percentile CPU, a 61st-percentile GPU, and a combined percentile of 77 — an upper-tier mobile compute platform whose overall rank is held back from the CPU's individual elite standing by its mid-pack graphics. In the database's composite terms, this is a top-quartile system overall with a top-decile processor at its heart.

Upgrade Path and Platform

The platform anchors are AMD Socket FP11, LPDDR5X on a quad-channel bus at 256.0 GB/s, and PCIe Gen 4 with 16 CPU lanes. LPDDR5X is typically soldered in laptop implementations, so memory expansion is a build-time decision rather than an upgrade path — buyers should configure maximum memory capacity at purchase, since the GPU's system-shared memory draws from the same pool. The 16 Gen 4 lanes provide full-speed NVMe storage connectivity, which is the most impactful peripheral upgrade for developers and creators working with large assets.

Power headroom is straightforward: the CPU's TDP is 55 W and the GPU's is 15 W, with no power connectors and no suggested PSU figure because this is integrated, laptop-class silicon. There is no discrete-GPU upgrade within this build's power and thermal envelope. A sensible next upgrade is therefore a system-level move: within the database's rival data, the NVIDIA GeForce RTX 4060 sits 0.3 percent above the 780M on average score as a discrete option, though that represents a different class of machine. On the CPU side, the multiplier is locked, ruling out overclocking as a path; the realistic successor route is a newer Strix Halo-generation part on a compatible platform. In short: upgrade storage, plan memory at purchase, and treat graphics improvements as a future system purchase rather than a component swap.

Gaming Performance

To restate clearly: no measured FPS data exists for this exact CPU+GPU combination — the database's measuredFps field is empty and dataIsMeasured is false. Every frame-rate statement below is an estimate derived from the benchmark scores, not a measurement.

Working from those scores: the 780M's Steel Nomad DX12 result of 480, its 61st-percentile standing, and its average score of 17588 — within 0.5 percent of the Radeon Pro 560, Radeon Pro 460, and Radeon HD 7790 — sketch the expected envelope. At 1080p with high or ultra settings in modern AAA titles, frame rates should be modest and frequently below comfortable play thresholds, with the 12 RT cores making ray-traced presets impractical. At 720p-to-1080p with low-to-medium settings, or in esports-class and older titles, playable and potentially smooth frame rates become realistic, helped by the Vulkan-optimized driver behavior implied by the 33683 Vulkan score against 18602 for OpenCL. The CPU will never be the constraint: a 93rd-percentile processor with a 3967 PassMark single-thread score and 24 threads means frame pacing and draw-call throughput have vast headroom, so every frame lost is lost on the GPU side. Raising resolution shifts load onto the system-shared memory path — where 256.0 GB/s of quad-channel bandwidth is a genuine asset — but shading and fill-rate limits (8.909 TFLOPS, 92.80 GPixel/s, 139.2 GTexel/s) will dominate. The estimated verdict: a capable light-settings gaming machine attached to an exceptional compute engine, best understood as a professional laptop that can game casually rather than a gaming laptop that works.

Rate My PC: AMD Ryzen AI Max PRO 390 + AMD Radeon 780M

Apex Performer

System Balance Analysis

AMD Ryzen AI Max PRO 390

AMD Radeon 780M

Market Position

Game Performance Benchmarks

Cyberpunk 2077

Red Dead Redemption 2

Microsoft Flight Simulator

Control

Call of Duty: Warzone

Fortnite

Performance Insights

Optimal Performance

4K Gaming Ready

Performance Tiers Explained

Ultimate

High-End

Mid-Range

Entry Level

Legacy

CPU Analysis

Benchmark Performance

Usage Scenarios

FAQ

Balance and Bottleneck

Who Should Build It

GPU Analysis

Build Overview

Upgrade Path and Platform

Gaming Performance

4K Gaming Performance

Cyberpunk 2077

Red Dead Redemption 2

Microsoft Flight Simulator

Control

Call of Duty: Warzone

Fortnite

1440p Gaming Performance

Cyberpunk 2077

Red Dead Redemption 2

Microsoft Flight Simulator

Control

Call of Duty: Warzone

Fortnite

1080p Gaming Performance

Cyberpunk 2077

Red Dead Redemption 2

Microsoft Flight Simulator

Control

Call of Duty: Warzone

Fortnite

Related Processors

Related Graphics Cards

Compare Your CPU

Compare Your GPU

Related PC Builds

Same CPU with Different GPUs

Same GPU with Different CPUs

Other Popular Builds