NVIDIA adds eight-node DGX Spark clustering with 1TB unified memory
10/23/2026 — 10/23, 00:19·1 sources (all)·1 reports (all)
Key takeaways
- At GTC Berlin, NVIDIA announced support for eight-node DGX Spark clusters that scale unified memory to 1TB, enough to run frontier models su…
At GTC Berlin, NVIDIA announced support for eight-node DGX Spark clusters that scale unified memory to 1TB, enough to run frontier models such as GLM 5.3 (753B) locally. Eight-node clustering through NVIDIA Sync is due before the end of the year, and NVIDIA published scaling benchmarks for inference, orchestration and training.
Latest turnAt GTC Berlin, NVIDIA announced support for eight-node DGX Spark clusters, scaling unified memory to 1 TB and making it possible to run frontier models such as GLM 5.3 (753B) locally. Support for the clusters in NVIDIA Sync is slated for the end of the year, alongside benchmark data on how inference, orchestration and training scale.
- Heat index
- 91
- All sources
- 1
- All reports
- 1
- First seen
- 3 hours ago
Reports on this story headlines open the original
At GTC Berlin, NVIDIA announced support for eight-node DGX Spark clusters, scaling unified memory to 1 TB and making it possible to run frontier models such as GLM 5.3 (753B) locally. Support for the clusters in NVIDIA Sync is slated for the end of the year, alongside benchmark data on how inference, orchestration and training scale.
NVIDIA Developer BlogFirst-partyAI score 50
Other stories people are talking about
- Heat index 914RisingPHP 9.2-severity flaw details leak before patch, triggering global scramble12 sources
- Heat index 768RisingMeta's $825B spending pledge triggers AI stock selloff10 sources
- Heat index 722RisingAnthropic launches Claude Duet agent in research preview10 sources
- Heat index 673RisingDeepSeek closes roughly RMB 100B round with CATL and Tencent backing10 sources
- Heat index 633Google Cloud to deploy up to 960,000 Rubin GPUs14 sources
How is heat calculated?About the methodHide
Heat counts how many independent sources covered a story in the last 48 hours: one source counts once no matter how many posts it published, decaying with a 24-hour half-life. What ranks first is what many people are talking about.
This page aggregates public feeds. Headlines and summaries are machine-organized and remain the property of the original authors; verify important facts at the source. If you believe a headline or summary infringes your rights, email the contact address in the footer with the page URL and basis of your claim, and we will remove or replace it after review.
- Surge
- Discussion rising fast
- New
- First report within 6 hours
- Rising
- Still gathering discussion