FEVM Launches FA-EX9 Mini PC with AMD Ryzen AI Strix Halo to Challenge NVIDIA DGX Spark

Chinese manufacturer FEVM introduces the FA-EX9 mini PC, leveraging AMD´s latest Ryzen AI processor to deliver powerful Artificial Intelligence capabilities in a compact form factor.

Chinese PC maker FEVM has unveiled the FA-EX9 mini PC, marking a significant leap in compact workstation design by harnessing AMD´s new Ryzen AI MAX+ 395 ´Strix Halo´ processor. This high-performance chip delivers 16 Zen 5 CPU cores, 40 RDNA 3.5 graphics compute units, and an XDNA 2 neural engine capable of achieving 50 TOPS, all within a 2-liter chassis measuring 192 × 190 × 55 mm. The FA-EX9 is configured to sustain up to 120 W, placing it in performance contention with the Ryzen 9 9955HX and RTX 4070 Laptop GPU combination.

The system features 128 GB of LPDDR5X memory on a 256-bit bus, with as much as 96 GB assignable as video memory—suiting it well for large-model inference in Artificial Intelligence workloads. For storage, the FA-EX9 includes dual M.2 PCIe 4.0 SSD slots, accommodating up to 2 TB onboard and supporting up to 16 TB in total. Connectivity is robust with one HDMI 2.1, one DisplayPort 1.4, two USB4 Type-C ports enabling up to four 8K displays, and an OCuLink connector for external GPU expansion, catering to both edge Artificial Intelligence applications and creative professionals.

Inspiration for the FA-EX9 appears drawn from NVIDIA´s DGX Spark, a palm-sized Artificial Intelligence solution built around the GB10 Grace Blackwell superchip. The DGX Spark leverages a 20-core Arm CPU cluster and Blackwell GPU to achieve up to 1,000 FP4 Artificial Intelligence TOPS, supported by 128 GB unified LPDDR5X memory and up to 4 TB of secure NVMe storage in a 1.24-liter case consuming ~170 W. The FA-EX9, by contrast, delivers a more general-purpose platform with an emphasis on flexible expansion and wide-ranging usability, spanning Artificial Intelligence, workstation, and gaming tasks. While release dates and pricing for the FA-EX9 remain under wraps, the device is poised to become a versatile competitor in the burgeoning compact Artificial Intelligence hardware segment.

61

Impact Score

China still blocking Nvidia H200 chip sales

Nvidia has yet to complete H200 sales into China even after the United States reopened exports. Chinese authorities are reportedly limiting imports as Beijing pushes buyers toward domestic semiconductor suppliers.

OpenAI prepares GPT-5.5 launch

OpenAI is reportedly preparing GPT-5.5, its first fully retrained base model since GPT-4.5, as it pushes harder into enterprise software. The model is expected to bring native multimodal capabilities and stronger support for agent-based workflows.

Meta expands AWS Graviton deal for agentic Artificial Intelligence

Meta is expanding its partnership with AWS by deploying Graviton processors at scale for its next generation of Artificial Intelligence systems. The move highlights growing demand for CPU-heavy agentic Artificial Intelligence workloads alongside continued reliance on GPUs for model training.

Contact Us

Got questions? Use the form to contact us.

Contact Form

Clicking next sends a verification code to your email. After verifying, you can enter your message.