GLM-5.3-GGUF is a Hugging Face model repository containing quantized GGUF weights for the GLM language model. Developers can download and run the weights locally with compatible inference runtimes such as llama.cpp.
In the Quantised & converted weights space, GLM takes a focused approach. It focuses on running the GLM model locally without relying on hosted inference services. It is built as an open-source project for developers and machine learning practitioners. The project is open source (Apache-2.0). GLM is available on the command line, and it can be self-hosted.
Behind GLM is Unsloth, and it first shipped in 2023. Development happens publicly on GitHub with 75.5k stars and 2.6k commits in the last 90 days. Among its 5 catalogued features are quantized weights, GGUF format, and local inference.
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