KEY POINTS
- Agentic AI compact desktop: NVIDIA RTX Spark™ with up to 1 petaflop of FP4 performance and up to 128GB unified memory for local and private AI agents
- Round-the-clock operation: Compact 150 x 150 x 15mm (1.1-liter) chassis, built-in dual fans, and native Windows 11
- Agentic and creative ecosystems: Hermes Agent, ComfyUI, Adobe® Creative Cloud®, plus ASUS Zenni Claw and MuseTree
- Now available: 128GB and 64GB configurations; pricing and availability may vary by region
NEW DELHI, India — ASUS today announced the availability of the ProArt GR1X mini PC. Built on the NVIDIA RTX Spark™ superchip, ProArt GR1X is a Windows PC designed as an always-on home for local AI agents. It is able to run large models on-device, keep prompts and project files private, and work with the agent and creative tools people already use. ProArt GR1X can be specified with 128GB and 64GB of unified memory.
Built for agentic AI, powered by RTX Spark
AI agents work best when they can run continuously, see local files and apps, and use large models without per-token fees. ProArt GR1X is built for that job — its NVIDIA RTX Spark platform pairs a 6,144-core Blackwell RTX GPU with a 20-core Grace CPU over NVLink-C2C, sharing one pool of up to 128GB unified memory.
NVIDIA RTX Spark unites NVIDIA AI, RTX graphics, and unified memory in one slim, powerful Windows PC. Designed to run larger AI models locally — without cloud dependency — and move between creative work, development, and immersive gaming without missing a beat. Users can connect apps, tools, and workflows into one seamless experience. Private by default, RTX Spark brings NVIDIA’s full-stack AI platform, ready for the AI workloads of today and whatever comes next. All this is delivered on the familiar, trusted Windows platform.
Running AI locally means user data stays on the desk. ProArt GR1X supports 120B-parameter LLMs with up to 1 million tokens of context, so an agent can work through large projects, expansive codebases and complete projects with precision and accuracy. Personal data stays on the machine because there’s no upload to the cloud, and there are no per-token or per-generation fees because users can rely on local AI for more tasks, letting teams iterate more frequently.
Users decide where each task runs: fully local, in the cloud, or a hybrid based on performance, cost and privacy. ProArt GR1X runs NVIDIA CUDA natively on Windows 11, with RTX acceleration for 3D, video and AI apps and DLSS, as well as Reflex and ray tracing.
Built to run AI agents 24/7
ProArt GR1X measures 150 x 150 x 51mm and weighs 1.48kg, making it small enough to sit neatly beside a monitor. It is available in an anodized black finish or a sandblasted silver coat that resists fingerprint smudges.
A dual-fan system with 218 fan blades, 57 ultra-wide fins and four heat pipes handles the 140-watt TDP, with enhanced thermal coverage and seven-level fan control. This cooling is what allows ProArt GR1X to run 24/7 as an agent host.
ProArt GR1X offers a host of connectivity options to suit diverse workloads, boasting 10GbE LAN, WiFi 7 and Bluetooth® 5.4, four USB 3.2 Gen 2×2 Type-C® ports and HDMI® 2.1. It can drive up to four 4K displays, with HDMI output up to 8K, and offers dual M.2 NVMe® SSD slots with PCIe 5.0/4.0 support. Native Windows 11 means agent and creative workflows run without dual-boot or a separate Linux environment.
—





