Model · GLM · Reviewed June 2026

largeMIT753B paramsOpen weights

GLM-5.2

Z.ai (Zhipu AI) · GLM

753B parameter open-weight model. GLM-5.2 is a 753B MoE model requiring multi-GPU or distributed inference for full deployment; for consumer hardware, use the unsloth/GLM-5.2-GGUF 1-bit UD-IQ1 variants (~217–228 GB) via llama.cpp or Unsloth Studio with KTransformers for local execution at reduced fidelity.

Editorial review

Reviewed byOpenSourcesAI EditorialLast updatedJune 2026SourcesHuggingFace model card (zai-org/GLM-5.2), official docs, OpenSourcesAI editorial review.

VRAM figures are empirical estimates. Actual usage varies by runtime, context length, and system configuration. Verify on your specific hardware before production use.