---
license: mit
base_model:
- ArliAI/GLM-4.5-Air-Derestricted
---

Realized I never made a HALO quant of the funny model. Has MTP layers but llama.cpp does not support yet.

Check [4.6V](https://huggingface.co/Beinsezii/GLM-4.6V-GGUF-HALO) for details on this quant scheme.