GLM-5.3 Uncensored GGUF

Q4_K_M GGUF converted from dealignai/GLM-5.3-UNCENSORED-FP8.

The source is a 753B-parameter mixture-of-experts model.

Usage

This model overthinks. Add a reasoning-budget to limit the thinking tokens in llama.cpp, etc. or to the chat completion api call

See https://unsloth.ai/docs/models/glm-5.3 on how to run this locally

Files

See File folder for different Quants

Conversion

See https://huggingface.co/zai-org/GLM-5.3 for more info.

Thanks Z.ai for open sourcing this great model. Credit for the modified source weights belongs to dealignai. This repository ONLY provides the GGUF conversion.