AMD Strix Halo Memory Subsystem: Balancing CPU and GPU Demands for Mobile Performance
Editor’s Note (11/2/2025): Due to an error in moving the article over from Google Docs to Substack, the “Balancing CPU and GPU Bandwidth Demands” section was missing some Cyberpunk 2077 data.
Read the full articleYou might also wanna read
Setting up the AMD Strix Halo (Ryzen AI Max+ 395) mini-PC for local AI development
Setting up and getting up to speed with an AMD Strix Halo (Ryzen AI Max+ 395) mini-PC for local AI development.

AMD Ryzen AI Halo Review: A Dual-OS, 200B-Parameter Desktop Takes On the DGX Spark
AMD silicon arguably got here first: Strix Halo mini PCs and laptops were shipping with 128GB of unified memory well before NVIDIA entered t
Strix Halo Local AI Workstation Real World Performance Test
I tested the AMD Ryzen AI Max+ 395 (Strix Halo) against Mac Studio and a 4090 box on real local LLM workloads. Honest results, ROCm gaps inc
How high-bandwidth memory became a critical bottleneck for AI chip performance
High-bandwidth memory keeps powerful AI chips fed with data, and demand for it helped Boise-based Micron briefly top $1 trillion
Small AI Models on Smartphones Offer Alternative to Sovereign GPU Clusters
We need to build different artificial intelligence, on the devices people already carry, in the languages they already speak.
South Korea's GPU Race: Why AI Competitiveness Depends on Utilization, Not Just Hardware
Korea is rapidly expanding AI GPU capacity, but infrastructure competitiveness may also depend on utilization, orchestration, and access, no

Comments
Sign in to join the conversation.
No comments yet. Be the first.