MaliAir author hub
GLM 5.2 BF16 → mxfp4 moe Mixed Precision Quantization + Sharded This repository contains a quantized and sharded version of the GLM 5.2 base model originally in BF16 , converted to the GGUF format using llama.cpp . To make the model both efficient and practical for deployment , …
Models
2
Downloads
513
Run models locally with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.