TECHNOLOGY AT A GLANCE

Explore the capabilities

AI development power, sized for the desktop

The Acer Veriton GN100 delivers serious local AI capability in a compact mini workstation. Develop, test, and run compatible AI workloads close to your data, then expand into a larger environment when your requirements grow.

128GB Unified Memory

128GB of LPDDR5x coherent unified memory provides shared memory for the CPU and GPU to support demanding AI development and inference workloads.

Local AI Development

A 2TB M.2 NVMe SSD provides local storage for models, datasets, and projects. NVIDIA DGX OS supports a development environment for prototyping, fine-tuning, and running AI models.

Connect Two Systems

NVIDIA ConnectX-7 networking enables two Acer Veriton GN100 workstations to connect for larger AI workloads, with Acer supporting AI models up to 405 billion parameters, depending on model and configuration.

Built for Local AI Development

Bring AI development to your desktop with the Acer Veriton GN100. NVIDIA GB10 Grace Blackwell performance, 128GB of unified memory, and 2TB of NVMe storage give developers and researchers a compact platform to prototype, fine-tune, and run AI models locally.

With NVIDIA DGX OS and support for tools such as PyTorch, Jupyter, and Ollama, you can build and test your next AI project while keeping models and datasets on your own system.

TECHNICAL DETAILS

Built into the system

NVIDIA GB10 Grace Blackwell AI compute

The NVIDIA GB10 Grace Blackwell Superchip delivers up to 1 petaFLOP of AI performance at FP4 precision. It is designed to accelerate compatible local AI development, including prototyping, fine-tuning, inference, and experimentation.

128GB coherent unified memory

128GB of LPDDR5X coherent unified memory provides a shared memory architecture for the system. This helps support large local datasets and compatible AI models without separating work across traditional CPU and GPU memory pools.

2TB M.2 NVMe SSD storage

The included 2TB M.2 NVMe SSD provides fast local storage for AI models, datasets, development environments, and project files. It gives the system a practical capacity for getting started with local AI workflows.

NVIDIA DGX OS and AI software stack

NVIDIA DGX OS provides a purpose-built software environment for AI development. Use familiar tools and frameworks such as PyTorch, Jupyter, and Ollama to prototype, fine-tune, test, and run compatible workloads locally.

ConnectX-7 networking for expansion

NVIDIA ConnectX-7 networking provides a high-speed connection path for compatible multi-system environments. Connect two Veriton GN100 systems to scale local compute for compatible larger-model workflows.

Compact workstation design

The Veriton GN100 measures approximately 5.9 × 5.9 × 2 inches, bringing AI compute to desks, labs, classrooms, and small development environments without the footprint of a traditional server.