
Acer Veriton GN100 VGN100-UD13 AI Mini Workstation
Best price now
Prices are checked against each store and labelled with when.

Prices are checked against each store and labelled with when.
The Veriton GN100 is a compact AI workstation built around the NVIDIA GB10 Grace Blackwell Superchip. Its 20-core Arm CPU and Blackwell GPU share 128 GB of unified LPDDR5x memory over NVLink-C2C, so large models run on-device without copying data between CPU and GPU. A 2 TB NVMe drive, a ConnectX-7 NIC for linking two units, and NVIDIA DGX OS with PyTorch, Jupyter, Ollama and containerd make it a turnkey box for LLM development, RAG pipelines and agent building. It suits developers and small labs who want local, private model execution on a desk rather than a rack, and it competes with GPU workstations and cloud instances on convenience rather than raw expandability.
In stockReturn policy
The Acer Veriton GN100 is a mini AI workstation built around the NVIDIA GB10 Grace Blackwell Superchip. It combines a 20-core Arm CPU and a Blackwell GPU with 128 GB of coherent unified LPDDR5x memory and 2 TB of NVMe M.2 storage. The CPU and GPU share the memory pool through NVLink-C2C, allowing 200B-parameter models to run on-device without host-to-device copies.
The built-in NVIDIA ConnectX-7 NIC supports clustering two units into a larger memory pool for models up to roughly 405B parameters. The system comes preloaded with NVIDIA DGX OS and the NVIDIA AI software stack, including PyTorch, Jupyter, Ollama, and containerd. A Kensington lock slot and local model execution help keep data on the machine.
The chassis measures 5.9 inches square and 2.0 inches tall and weighs less than 1.5 kg (2.65 lb). It includes a keyboard and a 240 W external power adapter and is backed by a 3-year limited manufacturer warranty.
It checks today's price at every store, compares the alternatives and answers in about a minute.







