GLabs · Pro Grade
GLabs Edge AI
Inference and Capture at the Edge
Compact, ruggedized systems built to run AI inference where the data originates — factory floors, vehicles, field deployments, and camera networks — without a round trip to the cloud or the data center.
| Spec | Detail |
|---|---|
| Compute | Up to 275 TOPS (NVIDIA Jetson AGX Orin) |
| Enclosure | IP67-rated; fanless and ruggedized options |
| Power envelope | 15W–60W, configurable |
| Connectivity | GbE, CAN, GPIO, M.2 expansion |
| Software | GLIDS base image on every deployment, plus the GLabs AI Stack for AI workloads, GenesysBench™ validated |
| Deployment | GLIDS-validated, field-serviceable |
Also Available: NVIDIA DGX Spark — Deployed & Supported by GLabs
| Chip | NVIDIA GB10 Grace Blackwell Superchip |
|---|---|
| CPU | 20-core Arm (10× Cortex-X925 + 10× Cortex-A725) |
| Memory | 128GB unified LPDDR5x |
| Performance | 1 PFLOPS FP4 (500 TOPS dense) |
| Model scale | Up to 200B-parameter models locally; 2-unit NVLink pairing = 2 PFLOPS / 256GB |
| Storage | 4TB NVMe |
| Networking | ConnectX-7 200GbE, Wi-Fi 7 |
| Footprint | 150 × 150 × 50.5mm, 1.2kg |
| OS | NVIDIA DGX OS (Ubuntu 24.04) |
| Price (MSRP) | $4,699 |
Where It Shows Up
- Computer Vision & Video AI — real-time inference close to the camera, no round trip to the data center.
- AI Agents & Agentic Workflows — DGX Spark runs local agent frameworks and vector-store retrieval at the desk or the edge.
- Training & Simulation / XR-VR — field-deployable inference for immersive and simulation training environments.
Used across: AI Solutions (GLabs AI Stack), XR/VR
Tell us what you're building.
A solutions architect responds directly — no ticket queue.
Talk to a Solutions Architect