- Acer Veriton GN100 uses NVIDIA’s GB10 chip for extreme AI acceleration
- Acer’s mini workstation delivers one petaflop performance in a 1.2-kilogram chassis
- Two GN100 units can link together to manage huge model sizes
Acer has introduced the Veriton GN100 AI mini workstation, a small desktop device that claims to deliver up to 1 petaflop of FP4 AI performance.
It uses the Nvidia GB10 Grace Blackwell Superchip, bringing a level of processing power usually reserved for servers to business laptop and workstation users in compact office setups.
The company has opened early-access registration for UK organisations, presenting the system as a way to handle local AI workloads without relying heavily on cloud computing.
Desktop AI with enterprise ambitions
The Veriton GN100 appears to target professionals and researchers seeking powerful edge-based computation.
Measuring 150 by 150 by 50.5 mm and weighing about 1.2 kg, the device includes up to 128 GB of LPDDR5x unified memory for shared CPU-GPU access and 4 TB of self-encrypting NVMe storage.
Acer says two units can be connected using NVIDIA ConnectX-7 networking to manage large-scale models with up to 405 billion parameters.
The system runs NVIDIA DGX OS alongside the company’s AI software stack and supports development tools such as PyTorch, Jupyter, and Ollama.
This setup gives users an environment for prototyping and fine-tuning models directly on the desktop, removing the need for constant cloud access and helping reduce operational latency.
The Veriton GN100 integrates four USB 3.2 Type-C ports, HDMI 2.1b output, and an Ethernet interface for wired connectivity, alongside Wi-Fi 7 and Bluetooth 5.1 support.
Acer’s messaging emphasises privacy, cost control, and latency reduction, three areas where cloud-based AI services often fall short.
By enabling inference and data handling locally, the Veriton GN100 aims to keep sensitive data under internal governance, which is relevant for UK organisations bound by GDPR compliance.
The company also claims predictable expenses compared to fluctuating pay-per-use cloud pricing, though long-term cost comparisons remain untested.
This device targets enterprise environments that require high-speed on-device AI processing in a desktop form factor and includes a Kensington lock for added security.
This mobile workstation is listed from €3,999 in EMEA, with pricing and availability varying by region.
Follow TechRadar on Google News and add us as a preferred source to get our expert news, reviews, and opinion in your feeds. Make sure to click the Follow button!
And of course you can also follow TechRadar on TikTok for news, reviews, unboxings in video form, and get regular updates from us on WhatsApp too.
https://cdn.mos.cms.futurecdn.net/fCnpwVJ8ABvFuUJQACFCDD-1920-80.png
Source link
