Acer has unveiled the Veriton GN100 AI Mini Workstation at IFA Berlin 2025. Built on the NVIDIA GB10 Grace Blackwell Superchip, the compact workstation is engineered to deliver server-grade performance in a mini-PC form.
The Veriton GN100 reaches up to 1 PFLOPS of FP4 AI performance. It integrates next-generation CUDA cores, fifth-generation Tensor Cores, and 20 Arm-based CPU cores. The system also packs 128 GB of unified system memory and 4 TB of NVMe M.2 SSD storage, offering high-speed data access for demanding workloads.
Developers and researchers gain access to the NVIDIA AI software stack. It supports frameworks such as PyTorch, Jupyter, and Ollama, allowing efficient prototyping, fine-tuning, and deployment of large AI models. The workstation also enables local processing, reducing reliance on cloud services and lowering long-term costs.
Through NVIDIA ConnectX-7 NIC, two Veriton GN100 units can be linked, scaling capabilities to handle AI models with up to 405 billion parameters. Connectivity features include Wi-Fi 7, four USB 3.2 Type-C ports, HDMI, Ethernet, and security with a Kensington lock.
Exact pricing and availability details will vary by market. Customers are advised to contact Acer offices via www.acer.com
