](https://devquasar.com)
'Make knowledge free for everyone'
**EXPERIMENTAL**
You need to build llama.cpp from this [MR](https://github.com/ggml-org/llama.cpp/pull/27754)
Zero shot demo with Q5_K_M quantization

Quantized version of: [zai-org/GLM-5.3](https://huggingface.co/zai-org/GLM-5.3)