GIGABYTE Launches AI TOP ATOM Supercomputer Powered by NVIDIA GB10

Oct 14, 2025
GIGABYTE has announced that its AI TOP ATOM personal supercomputer, featuring the NVIDIA Grace Blackwell GB10 Superchip, will be available globally from October 15. The compact system delivers up to 1 PetaFLOP of FP4 AI performance and supports models with up to 200 billion parameters.

Taipei-based GIGABYTE has announced in a press release that its new AI TOP ATOM personal supercomputer will be available globally starting October 15. The system is built around the NVIDIA Grace Blackwell GB10 Superchip and is designed for local AI development, offering supercomputer-level performance in a desktop form factor.

The AI TOP ATOM comes with 128 GB of unified system memory, up to 4 TB of SSD storage, and delivers FP4 AI performance of up to 1 PetaFLOP. It supports large-scale models with up to 200 billion parameters and can be paired with another unit via an integrated NVIDIA ConnectX-7 network card to handle models with up to 405 billion parameters.

Preloaded with the NVIDIA AI Software Stack, the system enables rapid prototyping, fine-tuning, and inference. It also integrates with GIGABYTE’s AI TOP Utility software, providing a user interface for managing large language models, multimodal models, and machine learning applications. The AI TOP ATOM is aimed at developers, researchers, and institutions seeking a compact, energy-efficient AI computing solution.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Silicon Brief or Daily AI Brief.

Also, consider following us on social media:

AI Chips & Datacenters AI Brief AI Brief (X)
Free newsletter

Silicon Brief

Weekly coverage of AI hardware developments including chips, GPUs, cloud platforms, and data center technology.

Guide
Private AI chip companies, by latest reported valuation

Private AI chip companies, by latest reported valuation

Private companies building AI compute silicon (the chips that run AI workloads), shown with each company's most recent reported or disclosed valuation. The figures are measured on different dates and bases, so this is a snapshot, not a live ranking or a like-for-like comparison.

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.