Pandaily iconPandailySep 23, 2026

Inspur MetaBrain SD200 Ultra Packs 128 Domestic AI Chips for 2.8T Kimi K3 Under 5.85ms/Token

At AICC2026, Inspur Information launched the MetaBrain SD200 Ultra supernode with 128 tightly coupled domestic AI chips, 8 TB of unified accelerator memory and a claimed sub-5.85 ms/token latency running 2.8-trillion-parameter Kimi K3.

Inspur MetaBrain SD200 Ultra Packs 128 Domestic AI Chips for 2.8T Kimi K3 Under 5.85ms/Token
Read original More from Pandaily

Share this story

Send the public story page.

Useful takeaways from this story.

At AICC2026, Inspur Information launched the MetaBrain SD200 Ultra supernode with 128 tightly coupled domestic AI chips, 8 TB of unified accelerator memory and a claimed sub-5.85 ms/token latency running...

Building the complete brief

The page is ready to read now. The fuller skim-friendly version will appear here automatically.

The useful part

At AICC2026, Inspur Information launched the MetaBrain SD200 Ultra supernode with 128 tightly coupled domestic AI chips, 8 TB of unified accelerator memory and a claimed sub-5.85 ms/token latency running 2.8-trillion-parameter Kimi K3.

Details worth keeping

At AICC2026, Inspur Information launched the MetaBrain SD200 Ultra supernode with 128 tightly coupled domestic AI chips, 8 TB of unified accelerator memory and a claimed sub-5.85 ms/token latency running 2.8-trillion-parameter Kimi K3.

Keep reading in the app

Open the app view to save this story, compare related coverage, and continue from the same source.

Open in app