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 is a Foundation models & chat product. It focuses on providing an efficient, hardware-optimized version of the GLM-5.2 model for local or AMD-accelerated inference. GLM is an open-source project aimed at developers. The project is open source (Open Source). GLM is available on the web and API.
Behind GLM is AMD, and the product first shipped in 2025. Among its 3 catalogued features are Quantized Model, Tool Calling, and Reasoning Support.
Latest indexed changes and source events
amd/GLM-5.2-MXFP4 verified by the PulseGate indexer
Other apps tracked under the same category.
