AMD has introduced the Ryzen Artificial Intelligence Max 400 series for Artificial Intelligence development platforms as a refresh of the Ryzen Artificial Intelligence Max 300 series based on the Strix Halo design. The lineup combines up to 16 full-size Zen 5 CPU cores with a large SoC die that integrates an iGPU with 40 compute units based on the RDNA 3.5 graphics architecture, a 50 TOPS-class NPU, and a 4-channel (256-bit wide) LPDDR5X unified memory interface.
The series consists of three processor models, and all three include AMD PRO features positioned against Intel’s vPro. AMD is also planning consumer versions later this year. The main change in this refresh is memory support, with updated memory controllers on the Strix Halo SoC die that now support up to 192 GB of LPDDR5X memory. The previous Ryzen Artificial Intelligence Max 300 series tops out at 128 GB.
AMD is also emphasizing memory flexibility for graphics-heavy and development workloads. Users can manually partition the unified memory between the system and the iGPU, giving the latter up to 160 GB of video memory. Clock speeds have also increased, with the GPU reaching a maximum boost frequency of 3.00 GHz, up from 2.90 GHz on the Ryzen Artificial Intelligence Max 300 series, while the Zen 5 CPU cores now boost up to 5.20 GHz, up from 5.10 GHz on the previous generation.
The integrated NPU also receives a performance uplift. AMD says the NPU gets a 10% performance boost, now being capable of 55 TOPS. Taken together, the Ryzen Artificial Intelligence Max 400 series focuses on expanding memory headroom and raising peak performance across the CPU, GPU, and NPU while keeping the overall Strix Halo platform structure intact.