NVIDIA Unveils Local AI Hardware at GTC Berlin

21 October 2026 4 min read هدهد تك | Hudhud Tech

At GTC Berlin, NVIDIA showcased its complete range of local AI hardware. The recently launched RTX Spark powers personal agents on Windows PCs, while DGX Spark supports developers building and scaling applications on Linux. Additionally, DGX Station caters to enterprise teams handling frontier workloads on Linux, with a Windows version set to launch in December.

Key announcements include:

Underdog Desktop Agent now available for RTX Spark
DGX Spark 64GB available on Friday, Oct. 23
NVIDIA Sync to support eight DGX Sparks and add Model Launcher this month
October DGX Spark software update adds Wi-Fi Assistant and updates DGX Spark Skills
DGX Station improves manageability with seven new integrations
DGX Station for Windows launches in December with support for many manufacturing apps and agent harnesses
Three new open source reference workflows for robotics on DGX Station
NVIDIA Cloud Functions is coming in early access to DGX Station
Recursive Flint, a new local coding model, is now available for NVIDIA local hardware
Day-0 support for new Nemotron, GLM, DeepSeek, Qwen, MiniMax and FLUX.3 AI models
New accelerations for llama.cpp and vLLM inference engines and a new collection of checkpoints optimized for local AI hardware.

For more details on these local AI announcements, visit the GTC Berlin sessions.

RTX Spark Brings Personal Agents to the Windows PC

RTX Spark represents a new era for PCs, enabling personal agents, accelerated content creation, and 1440p gaming at 100 frames per second, with up to 128GB of unified memory and 1 petaflop of AI compute.

Early reviewers have praised the platform since its release on October 16:

“A dream machine for serious creators … ” — CGMag

“Designed for the future of AI … ” — The Verge

“An extremely capable, surprisingly portable and efficient machine … ” — PCMag

The Underdog desktop agent app, designed for fully local, private AI, is now available for RTX Spark. Powered by its Husky model-specific inference engine, Underdog runs models entirely on-device, ensuring user data remains private. It is available for download.

To facilitate developers and enthusiasts in building local agents, many RTX Spark laptops feature an unlocked bootloader.

During the GTC keynote, NVIDIA founder and CEO Jensen Huang demonstrated how AI agents on RTX Spark can train Hugging Face’s Microduck robot using NVIDIA Isaac Lab, Hermes Agent, and Nemotron 3.5 Bolt 74B.

Laptops from ASUS, Dell Technologies, HP, Lenovo, Microsoft, and MSI are available now, with Acer models coming soon.

Learn more about RTX Spark and access the latest RTX Spark playbooks.

DGX Spark Gives Developers Room to Build

The new DGX Spark 64GB systems, capable of running models such as Nemotron 3.5 Bolt 74B 24GB, Qwen3.8 27B, and Gemma 4 26B-A4B, will begin rolling out from partners on Friday, Oct. 23.

For workloads requiring additional capacity, developers can connect multiple DGX Spark systems using NVIDIA ConnectX-7 networking and NVIDIA Sync Cluster Assistant. This setup allows users to run advanced coding models like Qwen 3.8 Flash Next, DeepSeek v4 Flash 0731, and GLM 5.3 Flash.

DGX Spark now supports clusters of up to eight units in manual configuration, allowing for larger models, longer contexts, concurrent agents, and distributed development. This is ideal for small teams sharing a single cluster as a backend, enabling each developer to run concurrent sessions against the same model, delivering 1TB of unified memory — sufficient for frontier-class models like GLM 5.3.

Get started with the DGX Spark cluster playbook.

NVIDIA Sync Model Launcher will also be available later this month, simplifying access to local AI on a single DGX Spark or a cluster. Model Launcher facilitates model and container downloads suited to the configuration and connects them to OpenCode, automatically loading DGX Spark Skills for troubleshooting and maintenance.

The October DGX Spark software update introduces a new Wi-Fi Assistant, allowing users to switch networks while DGX Spark operates in appliance mode. Additionally, DGX Spark Skills provide workflow-focused guidance for troubleshooting and device maintenance directly within NVIDIA Sync via OpenCode.

DGX Spark systems are available from Acer, ASUS, Dell Technologies, GIGABYTE, HP, Lenovo, MSI, and NVIDIA.

DGX Station Puts Frontier Intelligence at the Desk

DGX Station offers 748GB of coherent memory and up to 20 petaflops of AI performance, enabling developers to run advanced models like GLM 5.3 and serve over 30 users at speeds comparable to cloud models. NVIDIA Sync now supports DGX Station, simplifying connections between two Linux-based systems.

New integrations with Absolute Security, Splunk by Cisco, Fleet Device Management, Microsoft Intune, Perforce Puppet, Progress Software Chef, and Tanium allow IT teams to manage DGX Station systems through enterprise setup and management processes, accelerating approvals and reducing deployment risks.

The upcoming Windows-based systems will enable developers to build workflows that utilize professional applications, operate from agents running large language models (LLMs) on NVIDIA GB300 systems, all within a single machine.

DGX Station for Windows, expected from system manufacturer partners in December, will extend local AI capabilities into existing enterprise applications and environments.