---
license: mit
tags:
- text-generation
base_model:
- zai-org/GLM-4.6
---
Introducing GLM-4.6-REAP-252B-A32B, a memory-efficient compressed variant of GLM-4.6 that maintains near-identical performance while being 30% lighter.

The original model available here: https://huggingface.co/cerebras/GLM-4.6-REAP-252B-A32B

Note: this is a MXFP4-MOE accurate downstream low-bit quantization version. It has been tested with the latest version of llama.cpp.

bitcoin:
```
bc1q6nvh39fcmy0de0ezepnn2z0rn4dme9yjal77ah
```