INFRASTRUCTURE◐ DEVELOPINGM · Material▲ Rising
ZTE pushes cheaper AI inference at MWC Shanghai
Jun 25, 2026SOURCE: theregister.com
SO WHAT
The window is moving from model demos to industrial throughput; cheaper inference is becoming the gatekeeper for who can scale.
Using OEX architecture SuperPODs and multi-dimensional co-design, ZTE says it is raising tokens per second while lowering total cost of ownership for scaled inference. The system was showcased at MWC Shanghai 2026.
This is Negative Resistance’s reframed reading of a reported signal. The headline and analysis above are our interpretation through the thousand-day-window lens. The original reporting lives at the source linked above.