Model Detail

GLM-5.2-mxfp4 is a large language model with 371.7B parameters released by mlx-community. The model is registered under the text-generation pipeline tag on Hugging Face.

GLM-5.2-mxfp4 ships with 371.7B parameters. Total weight footprint is approximately 743.4 GB, which is the relevant figure when planning local-inference VRAM.

GLM-5.2-mxfp4 is best fit for general-purpose chat and instruction-following workloads. Treat this as a starting matrix rather than a benchmark verdict — the right deployment usually depends on the specific evaluation suite that mirrors your workload.