# NVIDIA — Bringing the Spark to Europe: Local Intelligence Powers Next Wave of Agents

- Company: NVIDIA (nvidia.com)
- Announced: 2026-10-21T10:50:37+00:00
- Category: availability-change
- Coverage: not counted
- Announcement: yes
- Group: announcements
- Source: https://blogs.nvidia.com/blog/local-ai-gtc-rtx-dgx-spark-station-sync/
- Record: https://forck.live/items/25832-bringing-the-spark-to-europe-local-intelligence-powers-next-wave-of-agents
- Subject: AI platform
- Models affected: Nemotron 3.5 Bolt 74B, Qwen3.8 27B, Gemma 4 26B-A4B, Qwen 3.8 Flash Next, DeepSeek v4 Flash 0731, GLM 5.3 Flash, GLM 5.3, Recursive Flint, FLUX.3

NVIDIA is bringing its local AI hardware lineup to Europe at GTC Berlin, with RTX Spark for Windows PCs, DGX Spark for Linux developers and DGX Station for enterprise teams. RTX Spark, released October 16, runs personal agents, content creation and 1440p gaming with up to 128GB of unified memory and 1 petaflop of AI compute. New DGX Spark 64GB systems start rolling out from partners on Friday, Oct. 23, and can run models including Nemotron 3.5 Bolt 74B 24GB, Qwen3.8 27B and Gemma 4 26B-A4B. DGX Spark now supports clusters of up to eight units in manual configuration, delivering 1TB of unified memory, enough for frontier-class models like GLM 5.3. NVIDIA Sync Model Launcher arrives later this month, downloading a model and container suited to the configuration and connecting it to OpenCode. DGX Station offers 748GB of coherent memory and up to 20 petaflops, and a Windows version is expected from system manufacturer partners in December.

## Evidence

Verbatim from https://blogs.nvidia.com/blog/local-ai-gtc-rtx-dgx-spark-station-sync/:

> Now, DGX Spark supports clusters of up to eight units in manual configuration, enabling larger models, longer contexts, concurrent agents and distributed development. Ideal for small teams sharing a single cluster as a backend, with each developer running concurrent sessions against the same model, it delivers 1TB of unified memory — enough to run frontier-class models like GLM 5.3.

---

Record: https://forck.live/items/25832-bringing-the-spark-to-europe-local-intelligence-powers-next-wave-of-agents
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md