A.X K2 lands on Hugging Face with 688B total parameters and 33B active

_akhaliq · x · 2026-07-29

A.X K2 has been posted on Hugging Face as a large sparse MoE language model. The model card says it has 688B total parameters with 33B active parameters, is positioned as an agentic foundation model, and uses a Think-Fusion recipe that supports both a thinking mode and a lower-latency non-thinking mode. The card also says it is part of South Korea’s sovereign AI foundation model project.

Related event: South Korea Releases A.X K2, a 688B-Parameter Open-Source Model(2 posts)→

Original post →

More from Models

Models channel →