- Models
- GLM
Model family
GLM Models
GLM models from Z.ai are used for agentic engineering, tool use, coding, and reasoning workflows.
Best for
Agents
Use this family hub to compare GLM variants for agents workflows, then open the detail page for deeper deployment notes.
Code
Use this family hub to compare GLM variants for code workflows, then open the detail page for deeper deployment notes.
Reasoning
Use this family hub to compare GLM variants for reasoning workflows, then open the detail page for deeper deployment notes.
Source box
GLM family pages should verify exact Z.ai checkpoint names because GLM release status, API terms, and context windows differ by variant.
Verified through: June 2026
Model licenses, context windows, release names, and provider terms can vary by checkpoint. Verify the exact model card before production or commercial use.
Jump to
Variants
GLM models grouped by workflow
Latest / flagship
Coding
Compare
All GLM models in the directory
| Model | Type | Best for | Local runner notes | License | Detail |
|---|---|---|---|---|---|
| GLM-5.1 | Agents | Teams evaluating open-weight models for tool-calling, software engineering, and agent systems. | Full model is server-class; smaller Air or Flash style variants are usually better for local testing. | Check model card | Open |
| GLM-4.5 | Agents | Teams comparing prior GLM releases with current GLM-5.1 behavior. | Full model is server-class; Air or quantized builds are more practical. | Check model card | Open |
| GLM-5.2 | Code | GLM-5.2 is Z.ai's large mixture-of-experts model, aimed at coding, agentic tool-use, and very long context work rather than single-GPU home setups. | GLM-5.2 is a 753B MoE model requiring multi-GPU or distributed inference for full deployment. No official Ollama library tag (registry checked 2026-07-06). Below data-center scale, the unsloth/GLM-5.2-GGUF 1-bit UD-IQ1 variants (~217–228 GB) via llama.cpp or Unsloth Studio with KTransformers are the only local execution path, at reduced fidelity. Not consumer-local hardware friendly. | MIT | Open |