Z.ai's GLM-4.5-Air Packs 106B Agent Reasoning Into 12B Active Compute

Z.ai's 106B Mixture-of-Experts model activates just 12B parameters per token, trades a sliver of depth for cheaper inference, and ships under MIT.

Source

Z.ai

Published

Oct 21, 2026, 10:00 AM

Author

AlphaSignal Newsroom

Read

1 min read

Z.ai's 106B Mixture-of-Experts model activates just 12B parameters per token, trades a sliver of depth for cheaper inference, and ships under MIT.

Reporting is indexed from AlphaSignal. Rights remain with the original publisher and cited sources.

Next reads