AMD® Ryzen™ AI MAX+ 392

The AMD Ryzen AI MAX+ 392 is a laptop processor with 12 cores and 24 threads, built on the Zen 5 architecture (4 nm process). It launched in Jan 2026. Clocks run from 3.2 GHz base to 5.0 GHz boost. A 64-MB L3 cache backs the cores (6.4 MB per core). Maximum addressable memory is 128 GB. The chip drops into the FP11 socket and exposes PCIe 4.0 (16 lanes). Rated TDP is 55 W.

The AMD Ryzen AI MAX+ 392 scores 3,949 in single-core performance and 44,601 in multi-core performance (PassMark CPU Mark ratings). From those two ratings Feex computes 13,271 for overall performance, 34,519 for productivity performance, 31,639 for creator performance, 48,504 for engineering performance and 22,997 for gaming performance. Its multi-core throughput works out to 3,717 per core, 1,858 per thread and 811 per watt. Its computed efficiency index is 1,790. Its performance index is 164, so its overall performance is 64% above the Intel Core i5-12400 (index 100). Each bar shows the score as a share of a reference ceiling, which is the larger of the 99th-percentile score across the Feex CPU database and a fixed baseline.

Scores for individual PassMark CPU Mark test categories. Higher is better. These are measured test scores, not computed from the single-core and multi-core ratings.

In the individual workload tests the AMD Ryzen AI MAX+ 392 scores 153,881 in integer math, 100,066 in floating-point math, 551,412 in compression, 28,140 in cryptography, 3,039 in physics simulation, 45,424 in vector SIMD, 323 in the prime sieve and 60,011 in sorting. Higher is better. Compared with the Intel Core i5-12400, it is 161% above in integer math, 118% above in floating-point math, 142% above in compression, 145% above in cryptography, 179% above in physics simulation, 193% above in vector SIMD, 382% above in the prime sieve and 165% above in sorting. Each bar shows the score as a share of that workload's reference ceiling, the larger of the 99th-percentile score across CPUs with a recorded value and a fixed baseline.

The AMD Ryzen AI MAX+ 392 has 12 physical cores and runs 24 logical threads. It runs 2 threads per core. It runs at a base clock of 3.20 GHz and boosts up to 5.00 GHz.

The AMD Ryzen AI MAX+ 392 is a laptop processor, belongs to the AMD Ryzen AI Max family, uses the Zen 5 architecture, carries the codename Strix Halo and is manufactured on a 4 nm process. It launched in Jan 2026.

The AMD Ryzen AI MAX+ 392 has 960 KB of L1 cache, 12 MB of L2 cache and 64 MB of L3 cache. That adds up to about 76.9 MB of cache, or 6.41 MB per core. Each core has 1 MB of private L2 cache.

The AMD Ryzen AI MAX+ 392 has a 3-level cache hierarchy: L1 at 960 KB, L2 at 12 MB and L3 at 64 MB. L3 is the largest level and makes up about 83% of the cache listed here.

The AMD Ryzen AI MAX+ 392 addresses up to 128 GB of memory and uses 4 memory channels.

The AMD Ryzen AI MAX+ 392 uses the FP11 socket, supports PCI Express 4.0 and provides up to 16 PCIe lanes.

The AMD Ryzen AI MAX+ 392 has a rated TDP of 55 W.

Instruction sets, security, virtualization, AI acceleration and OS readiness. Features are listed as supported, explicitly not supported, or not recorded; a feature that is not recorded is not the same as unsupported.

The AMD Ryzen AI MAX+ 392 is manufactured by TSMC.

The AMD Ryzen AI MAX+ 392 is also identified by the model number 392.

After an audit, 1 value was corrected and 1 empty field was filled on the AMD Ryzen AI MAX+ 392 record. Each change is listed with its old value, new value, rule and sources.

• L2 cache (total): 1,024 KB → 12,288 KB. Rule: L2 cache was stored per core. stored equals the per-core size in PassMark "12 x 1024 KB". Sources: PassMark: AMD RYZEN AI MAX+ 392; Wikipedia: List of AMD Ryzen processors (revision 1376710910).

The audit log is public: all changes for this CPU, the corrections overview and the method.

Feex has recorded 51% of the specifications it tracks for the AMD Ryzen AI MAX+ 392. Values Feex does not hold are shown as "Not recorded" rather than estimated.

Not recorded: Core Configuration: Efficiency Cores, Hybrid Architecture, All-Core Boost and Unlocked Multiplier. Architecture & Generation: ISA Family and Market Status. Cache: L4 Cache. Memory Support: Memory Bandwidth, DDR5 Support, DDR4 Support, LPDDR Support, ECC Memory and Max Memory Speed. Graphics: Integrated Graphics, Graphics Model, Graphics Base Clock, Graphics Max Clock, Execution Units, Display Outputs and Max Video Memory. Platform & Compatibility: Package and Package Size. Power & Thermals: Base Power, Maximum Turbo Power, Configurable TDP (Min), Configurable TDP (Max), Max Junction Temperature and Tcase. Physical & Manufacturing: Transistor Count, Die Size, Die Count and Launch Price. Naming & Aliases: SKU, Processor Number and Part Number.

Processors that use the same FP11 socket as the AMD Ryzen AI MAX+ 392 and have the closest multi-core scores in the Feex database include AMD Ryzen AI Max Pro 390, AMD Ryzen AI Max 390, AMD Ryzen AI Max+ 395, AMD Ryzen AI Max 385 and AMD Ryzen AI Max Pro 385.