SYSTEM ANALYZER

Rate My PC: AMD Ryzen AI Max 390 + AMD Radeon 740M

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

91 / 100
ULTIMATE READY

Apex Performer

Top 9% 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
95%
VS
GPU
88%
PROCESSOR

AMD Ryzen AI Max 390

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

AMD Radeon 740M

12,870 Benchmark Score
Top 12% 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

# CPU Analysis

The AMD Ryzen AI Max 390 is a 12-core, 24-thread mobile processor built on the Zen 5 architecture, using the Strix Halo codename and manufactured on TSMC's 4 nm process. The chip consists of two CCDs, each measuring 70.6 mm², and operates with a base clock of 3.20 GHz and a boost clock of 5.00 GHz. Cache hierarchy is substantial: 80 KB of L1 per core, 1 MB of L2 per core, and a shared 64 MB L3 pool. This configuration places the Ryzen AI Max 390 in the 91st percentile among all CPUs, indicating that it outperforms roughly nine out of ten processors in the database.

Benchmark results reinforce this high standing. In Cinebench R23, the chip scores 36,064 points in multi-core and 5,091 in single-core. The multi-core figure is particularly telling for heavily threaded workloads like video encoding or 3D rendering, where the 24 threads can be fully utilized. The single-core score of 5,091 suggests strong per-thread performance, which matters for applications that rely on responsiveness in lightly threaded tasks, such as spreadsheet recalculation or script execution. In Cinebench R20, the scores are 15,146 multi-core and 2,138 single-core, while Cinebench R15 shows 3,635 multi-core and 513 single-core. The scaling from R15 to R23 is consistent, with the multi-core gains tracking the increased thread count and clock behavior.

PassMark results add another dimension. The multithread score is 41,737, and the single-thread score is 4,028. Data compression scores 487,145, which is extremely high and points to strong integer throughput — useful for file archiving or database operations. Data encryption scores 25,097, extended instructions 38,716, and floating-point math 90,594. Integer math is particularly strong at 146,519, while physics comes in at 2,761 and prime number finding at 316. The random string sorting score of 53,113 indicates solid memory subsystem performance, which aligns with the quad-channel LPDDR5X support. The average benchmark score across all tests is 56,273.

Comparing to nearest rivals, the Ryzen AI Max 390 sits within a tight cluster. The AMD Ryzen AI 9 HX PRO 470 scores 56,306, which is just 0.1% higher. The Intel Core i9-14900HX scores 56,004, placing it 0.5% behind. The AMD Ryzen Threadripper PRO 3955WX scores 56,555, which is 0.5% ahead, and the Intel Core 7 253PQE scores 55,919, coming in 0.6% behind. These deltas are negligible in real-world terms — the Ryzen AI Max 390 is effectively performance-equivalent to a high-end desktop Threadripper PRO in aggregate benchmarks, which is remarkable for a 55 W mobile part. The practical takeaway: this CPU can handle sustained multi-core loads without falling behind desktop-class competitors, though the 55 W TDP will influence thermal behavior in a laptop chassis.

# Benchmark Performance

The CPU's average benchmark score of 56,273 places it at the 91st percentile, a strong showing for a mobile processor. The GPU, an AMD Radeon 740M, achieves an average benchmark score of 12,870 across Geekbench OpenCL and Vulkan tests, landing at the 53rd percentile among all GPUs. The combined percentile for the CPU+GPU pairing is 72, which reflects a system that is heavily CPU-dominant in overall benchmark terms.

For the GPU specifically, the Geekbench OpenCL score is 10,172, and the Vulkan score is 15,568. The Vulkan result being notably higher than OpenCL suggests the RDNA 3.0 architecture performs better with modern graphics APIs, which is relevant for gaming and compute workloads that leverage Vulkan. The GPU's nearest rivals include the AMD FirePro W5100 at 12,847 (0.2% higher), AMD Radeon Pro 455 at 12,831 (0.3% higher), NVIDIA GeForce GTX 590 at 12,830 (0.3% higher), and AMD Radeon RX 580 at 12,928 (0.4% lower). These deltas indicate the Radeon 740M is essentially on par with older discrete desktop GPUs like the RX 580, despite being an integrated part. However, the 53rd percentile means half of all GPUs outperform it, so expectations must be tempered for demanding graphics workloads.

The combined picture is one of asymmetry. The CPU sits near the top of the database, while the GPU sits near the middle. This means the system will excel at CPU-bound tasks — compilation, rendering, data processing — but will trail in GPU-bound scenarios like high-resolution gaming or GPU-accelerated rendering. The average benchmark scores reflect this split: the CPU's 56,273 is a high-end figure, while the GPU's 12,870 is mid-range. Users should interpret the 72nd combined percentile as a system that is better suited to compute-heavy tasks than to graphics-intensive ones.

It is important to note that the FACT PACK contains no measured FPS data for this exact CPU+GPU combination. All FPS discussions in this analysis are therefore estimates derived from the benchmark scores, not from direct game testing.

# Balance and Bottleneck

The data indicates a clear CPU-favored balance. The CPU's 91st percentile versus the GPU's 53rd percentile means the processor is capable of feeding far more work than the integrated graphics can process. In CPU-bound workloads — such as code compilation, 3D scene setup, or physics simulation — the Ryzen AI Max 390 will perform at a level near desktop high-end parts, as evidenced by its proximity to the Threadripper PRO 3955WX (0.5% delta). The GPU will not hinder these tasks.

Conversely, in GPU-bound workloads — like gaming at high resolutions or GPU-accelerated rendering — the Radeon 740M becomes the limiting factor. The GPU's 2.867 TFLOPS FP32 throughput and 8 ROPs are modest figures, and the 53rd percentile confirms it is a mid-tier integrated solution. The CPU will likely sit idle waiting for the GPU to complete frame rendering or compute tasks, creating a bottleneck that cannot be overcome by the processor's strength.

The memory bandwidth of 256.0 GB/s from quad-channel LPDDR5X helps mitigate this imbalance somewhat, as the GPU shares system memory and benefits from high bandwidth. However, the system-shared memory type and system-dependent bandwidth mean the GPU's performance is tied to the CPU's memory configuration. The pixel rate of 22.40 GPixel/s and texture rate of 44.80 GTexel/s are consistent with a 256-shading-unit design, but they are not sufficient for high-refresh gaming at demanding settings.

For FPS scaling, without measured data, we can infer from the GPU's Vulkan score of 15,568 that the system can handle esports titles at lower settings, but modern AAA games will require significant compromises. The CPU will not be the limiting factor in any gaming scenario; the GPU will always be the first constraint. In productivity, the reverse is true — the GPU is sufficient for display output and basic acceleration, while the CPU does the heavy lifting.

# Who Should Build It

This pairing targets users who need substantial CPU compute in a laptop form factor without requiring high-end discrete graphics. The 91st percentile CPU makes it ideal for software developers who compile large codebases, data scientists running analysis scripts, or engineers using simulation tools that are single-threaded or moderately threaded. The Cinebench R23 multi-core score of 36,064 and PassMark multithread score of 41,737 indicate sustained performance for long compile jobs or batch processing.

Content creators who work primarily with CPU-based workflows — such as audio processing, video encoding with x264/x265, or 3D modeling before rendering — will benefit from the 12 cores and 24 threads. The PassMark data compression score of 487,145 is particularly relevant for media archiving or large file transfers. Students in computer science or engineering fields will find the CPU capable of running virtual machines or heavy IDEs, and the 256.0 GB/s memory bandwidth supports memory-intensive workloads like large dataset manipulation.

Small business workstations that handle spreadsheets, databases, or ERP systems will see excellent responsiveness, given the single-thread score of 4,028 in PassMark. The CPU's 91st percentile means it outperforms most desktop processors in general office tasks, making it a future-proof choice for multi-year deployments. Gamers, however, should look elsewhere unless they play undemanding titles — the GPU's 53rd percentile will cap frame rates well below what the CPU can support. For users who occasionally game but primarily need a compute powerhouse, this is a viable trade-off, but dedicated gaming laptops with discrete GPUs will offer better graphics performance.

# Upgrade Path and Platform

The Ryzen AI Max 390 uses the AMD Socket FP11, which is a mobile platform. The memory support is LPDDR5X with a quad-channel bus and 256.0 GB/s bandwidth, and ECC is supported. The PCIe interface is Gen 4 with 16 lanes from the CPU, which provides adequate bandwidth for high-speed NVMe storage or external GPU enclosures, though the laptop form factor limits expansion options.

The CPU's TDP is 55 W, and the GPU's TDP is 45 W, for a combined 100 W thermal envelope. The GPU's suggested PSU is listed as null, which is typical for an integrated part — no dedicated power supply is needed. The GPU uses no power connectors and is an IGP slot width, meaning it is soldered or integrated onto the motherboard. This limits upgradeability: neither the CPU nor GPU can be swapped in most laptop designs.

A sensible next upgrade path is limited to external components. Users could add an external GPU via the PCIe Gen 4 x8 interface (the GPU's bus interface) or the CPU's 16 lanes, though the laptop form factor may not support this. Memory is also fixed, as LPDDR5X is typically soldered. The platform is therefore best viewed as a closed system where the initial configuration is the final configuration. For those needing more graphics performance, the only option is to move to a different laptop with discrete graphics. The CPU itself has no unlocked multiplier, so overclocking is not possible.

# FAQ

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

A: The AMD Ryzen AI Max 390 has 12 cores and 24 threads, based on the Zen 5 architecture.

Q: How does the CPU compare to its nearest rival?

A: The CPU's average benchmark score of 56,273 is 0.1% lower than the AMD Ryzen AI 9 HX PRO 470 (56,306) and 0.5% higher than the Intel Core i9-14900HX (56,004).

Q: What is the GPU's benchmark position?

A: The AMD Radeon 740M has an average score of 12,870, placing it at the 53rd percentile among all GPUs.

Q: Does this system support ECC memory?

A: Yes, the CPU supports ECC memory, and the memory type is LPDDR5X with a quad-channel bus.

Q: What is the GPU's architecture and process node?

A: The GPU uses RDNA 3.0 architecture on a 4 nm process from TSMC, with 256 shading units and 4 RT cores.

Q: Are there measured FPS data for this combination?

A: No, the FACT PACK contains no measured FPS data for this CPU+GPU pairing, so all FPS figures are estimates.

Q: What is the system's combined percentile?

A: The combined percentile for the CPU and GPU is 72, indicating a system that is strong overall but heavily CPU-dominant.

# GPU Analysis

The AMD Radeon 740M is an integrated GPU based on the RDNA 3.0 architecture, using the Phoenix2 chip and manufactured on TSMC's 4 nm process. The chip contains 20,900 million transistors on a 137 mm² die, with a transistor density of 152.6 million per square millimeter. Clock speeds are 800 MHz base and 2800 MHz boost. Memory is system-shared, with the bus width and bandwidth listed as system-dependent, meaning performance scales with the CPU's LPDDR5X configuration — in this case, the 256.0 GB/s quad-channel bandwidth.

The GPU has 256 shading units, 16 texture mapping units, and 8 ROPs. It includes 4 RT cores for ray tracing, but no tensor cores. The pixel rate is 22.40 GPixel/s, and the texture rate is 44.80 GTexel/s. FP32 throughput is 2.867 TFLOPS, with FP16 at the same 2.867 TFLOPS (1:1 ratio). The bus interface is PCIe 4.0 x8, and the TDP is 45 W. The GPU supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Benchmark results show a Geekbench OpenCL score of 10,172 and a Vulkan score of 15,568. The higher Vulkan score suggests the RDNA 3.0 architecture is well-optimized for modern APIs, which is beneficial for games that use Vulkan. The average score of 12,870 places the GPU at the 53rd percentile. Nearest rivals include the AMD FirePro W5100 (12,847, 0.2% higher), AMD Radeon Pro 455 (12,831, 0.3% higher), NVIDIA GeForce GTX 590 (12,830, 0.3% higher), and AMD Radeon RX 580 (12,928, 0.4% lower). These comparisons show the 740M matches older mid-range discrete GPUs, but it is not competitive with modern discrete solutions.

For rendering workloads, the 2.867 TFLOPS FP32 performance is adequate for basic 3D previews or light GPU rendering, but it will struggle with complex scenes. The 4 RT cores offer some ray tracing capability, but the low shading unit count means ray-traced effects will be limited. The system-shared memory with 256.0 GB/s bandwidth is a positive factor, as it provides more bandwidth than many discrete GPUs from a few years ago, but the shared nature means the CPU and GPU compete for the same memory resources.

# Build Overview

This build pairs the AMD Ryzen AI Max 390 CPU with the AMD Radeon 740M integrated GPU in a laptop form factor. The CPU is a 12-core, 24-thread Zen 5 part with a 55 W TDP, and the GPU is an RDNA 3.0 integrated solution with a 45 W TDP. The combined thermal envelope is 100 W, which is reasonable for a high-performance laptop.

The system's combined percentile is 72, placing it in the upper-middle tier of all CPU+GPU combinations. This tier reflects a machine that excels at CPU-intensive work but is average for graphics. The CPU's 91st percentile and GPU's 53rd percentile create a wide gap, which is the defining characteristic of this build. It is not a gaming laptop; it is a mobile workstation with acceptable graphics for basic tasks.

The GPU's average benchmark score of 12,870 and the CPU's 56,273 tell the story: this system is about compute, not graphics. For users who need a powerful processor in a laptop and can tolerate integrated graphics, this pairing is sensible. For those expecting gaming or GPU rendering, it will disappoint.

# Gaming Performance

No measured FPS data exists for this exact CPU+GPU combination, so all frame rate figures discussed here are estimates derived from the GPU's benchmark scores and should be treated as approximations, not verified results.

Based on the GPU's 53rd percentile and Vulkan score of 15,568, this system can handle esports titles like CS:GO or League of Legends at low-to-medium settings with playable frame rates, likely in the 60-90 FPS range at 1080p. The CPU's strength ensures that frame pacing will be consistent, with no CPU-induced stutters. For older AAA games from several years ago, the 740M might manage 30-40 FPS at 1080p with low settings, but modern AAA titles will be challenging, often requiring 720p or significantly reduced settings to reach 30 FPS.

At 1440p or 4K, gaming is not viable for demanding titles, as the GPU's 8 ROPs and 2.867 TFLOPS will limit fill rate and compute. The 256.0 GB/s memory bandwidth helps, but the system-shared memory and the GPU's modest compute are hard constraints. The CPU will never be the bottleneck in any gaming scenario; the GPU limits all graphics performance. Users should plan for light gaming only, and for any serious gaming, a discrete GPU is necessary.

# Usage Scenarios

High-refresh gaming: Not recommended. The GPU's 53rd percentile and 2.867 TFLOPS FP32 throughput cannot sustain high frame rates at 1080p in modern games. Esports titles may approach 60 FPS at low settings, but 144 Hz or 240 Hz displays will go unused.

Streaming: The CPU's 12 cores and 24 threads are excellent for software encoding, with a Cinebench R23 multi-core score of 36,064 indicating ample headroom for x264 encoding alongside a game. The GPU's lack of tensor cores means no hardware-accelerated encoding benefits, but the CPU can handle it.

Video editing: The CPU's PassMark multithread score of 41,737 and data compression score of 487,145 make it strong for video editing timelines and export. The GPU's 53rd percentile will slow down effects-heavy editing or GPU-accelerated renders, but basic edits and color grading will be smooth.

3D rendering: CPU-based rendering, such as in Blender's Cycles engine, will benefit from the 24 threads. The GPU's 2.867 TFLOPS is too weak for GPU rendering, so users should stick to CPU rendering, where the Ryzen AI Max 390 performs near desktop high-end parts.

Software development: The CPU's 91st percentile and single-thread score of 4,028 in PassMark make it ideal for compilation, IDE responsiveness, and running tests. The 64 MB L3 cache helps with large codebases, and the 256.0 GB/s memory bandwidth supports fast builds.

Student and office work: Overkill for most tasks, but the CPU's high single-thread performance ensures snappy application launches and multitasking. The GPU is sufficient for document editing and web browsing, and the 55 W TDP means battery life should be reasonable in a laptop.