- Acer Veriton GN100 uses NVIDIA GB10 Superchip with 128 GB memory and 4TB storage
- Compact design below 1.5 kg still supplies 1 pflops of FP4 AI –
- Two affiliated system scale for handling AI models with up to 405 billion parameters
Acer has announced Veriton GN100 AI Mini Workstation, a compact desktop built on Nvidia’s GB10 Grace Blackwell Superchip.
It is designed to run large AI models locally with the possibility of scaling workloads further by linking two systems together.
Veriton GN100, which was revealed at IFA 2025 in Berlin, delivers up to 1 pflops FP4 AI performance through a combination of 20 arm-based CPU cores, cuda nuclei and fifth generation of tensal cores.
Up to 405 billion parameters
The unit comes with 128 GB of Unified LPDDR5X memory and 4TB self-encrypting NVME storage.
Despite its diminishing 150 mm x 150 mm footprint and below 1.5 kg of weight, Veriton GN100 is designed to deliver server class calculation effect in a mini-PC form factor.
The system includes NVIDIAS AI Software Stack and DGX BASE OS with support for commonly used developer tools such as Pytorch, Jupyter and Ollama.
Acer says this will allow developers, researchers and students to prototype, fine -tune and test large language models directly on the system, reducing the addiction of external cloud infrastructure and helping lower operating costs.
With an NVIDIA ConnectX-7 SMARTNIC installed, two Veriton GN100 devices can be linked further to scale workloads, allowing the treatment of AI models with up to 405 billion parameters.
This will make it possible to work with even larger training kits and experiments without requiring immediate access to data center hardware.
Connection includes four USB 3.2 Type-C ports, HDMI 2.1B, Ethernet, Wi-Fi 7 and Bluetooth 5.1.
Security features include a Kensington lock and local execution of AI models to help protect sensitive data.
Acer has set prices for Veriton GN100 to $ 3,999 in North America and € 3,999 in EMEA, with availability varying by region.
Acer is just the latest PC manufacturer launching an NVIDIA DGX Spark clone that follows in the footsteps of ASUS, HP and Dell and MSI.
