An AMD-published quantized version of the GLM-5.2 large language model using MXFP4 precision. The repository includes chat templates supporting tool use, reasoning effort levels, and system prompts. It is designed for compatibility with Hugging Face pipelines and AMD inference runtimes.
GLM sits in PulseGate's Foundation models & chat category. It focuses on providing an efficient, hardware-optimized version of the GLM-5.2 model for local or AMD-accelerated inference. It is built as an open-source project for developers. GLM is open source under the Open Source license. GLM is available on the web and API.
Behind GLM is AMD. Among its 3 catalogued features are Quantized Model, Tool Calling, and Reasoning Support.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do