K2-Horizon GGUF Quantizations Released

·2026.09.23 05:26

Key point

GGUF quantization files for the K2-Horizon model family have been released, but a forked version of llama.cpp is currently required.

Details

The IFM organization on Hugging Face has released GGUF quantization files for the K2-Horizon model family. The available models include MoVA-36B-A4B, 32B, 7B, 3.7B, and 0.9B, totaling five variants.

However, since the official llama.cpp PR to support these models has not yet been merged, users must use the llama.cpp fork version distributed by the developer.

quantization gguf llama.cpp open-source-model k2-horizon hugging-face

Read originalShare on Threads

This summary was generated automatically by AI. Check the original for the author's claims and context. Copyright belongs to the original author.

Our guide explains how the AI works. Report summary errors, attribution issues, or removal requests via Contact.