MSI EdgeXpert MS-C931: Compact Desktop Supercomputer with Grace Blackwell

LinkMSI USATool

MSI has introduced the EdgeXpert MS-C931, a compact desktop AI system powered by Nvidia's GB10 Grace Blackwell Superchip. The system delivers up to 1 PetaFLOP of FP4 tensor performance and features 128GB of unified memory.

Key points

  1. Powered by the Nvidia GB10 Grace Blackwell Superchip with a 20-core Arm CPU (10 Cortex-X925 and 10 Cortex-A725).
  2. Provides 1 PetaFLOP of AI tensor performance (1,000 TOPS FP4 sparse) and 128GB LPDDR5x unified memory with 273 GB/s bandwidth.
  3. Capable of running models up to 200B parameters locally, scalable up to 405B parameters across dual linked units via ConnectX networking.
  4. Ultra-compact 1.19-litre form factor (151 x 151 x 52 mm) weighing 1.2 kg, running Nvidia DGX OS.
  5. Comprehensive I/O including 10GbE, ConnectX-7 SmartNIC, Wi-Fi 7, four USB-C ports, and a 4TB self-encrypting NVMe SSD.

Why it matters

Running massive language models locally typically requires data centre racks or remote cloud infrastructure. Small-footprint machines with unified high-speed memory enable development teams to keep sensitive data on-premises with low latency while retaining a direct migration path to DGX clouds.

Analysis

MSI targets edge and robotics engineers using Nvidia Isaac, Metropolis, and Holoscan frameworks. By integrating NVLink-C2C and ConnectX-7 SmartNICs, multiple systems can be stacked to run 405B-parameter models directly at the desk, bridging the gap between local prototyping and large-scale cloud deployments.

Mentioned links

Found in

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • Video

    Video:Heavy Metal Cloud

    Nvidia DGX Spark Hands-On: Setup, vLLM Serving, and Mac Studio Comparison

    Heavy Metal Cloud reviews the Gigabyte and ASUS Nvidia DGX Spark desktop units powered by the Grace Blackwell architecture. The video provides a step-by-step guide for local LLM serving using Docker, vLLM, and SparkRun, as well as media generation in ComfyUI, comparing real-world performance against a Mac Studio.

    AI & LLMs· Tutorial

  • Link:NVIDIA

    NVIDIA DGX Spark Developer Hub: Workflows for GB10 Grace Blackwell Superchip

    NVIDIA has launched the DGX Spark Developer Hub, offering playbooks and guides for running AI agent workflows on the NVIDIA GB10 Grace Blackwell Superchip. The hub features quickstarts for tools such as Open-WebUI, ComfyUI, and vLLM alongside multi-Spark networking setups.

    AI & LLMs· Resource

  • Video

    Video:AIProgrammingHardware

    Essential Software Ecosystem and GitHub Repositories for NVIDIA DGX Spark

    This video details the primary open-source software repositories and workflows for NVIDIA's DGX Spark desktop AI supercomputer. Powered by the GB10 Grace Blackwell Superchip with 128 GB of unified memory, the hardware enables private local LLM inference, multi-agent setups, and model training without cloud reliance.

    AI & LLMs· Resource

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.