---
license: mit
base_model:
- zai-org/GLM-5.2
library_name: transformers
tags:
- compressed-tensors
- llm-compressor
- vllm
- mxfp4
---

## RedHatAI/GLM-5.2-MXFP4xFP8_BLOCK

GLM5.2 quantized with RTN with MXFP4 MoE and FP8 block activations, and other weights quantized to FP8 block. This model is experimentally supported in vLLM.