The publication AI reads — a remote MCP server, nothing to install.Connect your agent →

zai-org/GLM-5.1

zai-org/GLM-5.1 is a zai-org record on this register. The Hugging Face model API lists the pipeline tag as text-generation. The safetensors index gives an exact parameter count of 753,864,139,008. Architectural context length (max_position_embeddings) is 202,752. The listed licence is mit. The Hub repository was created on 3 Apr 2026, which is the release date this register uses.

Primary source: the Hugging Face model card for zai-org/GLM-5.1. Fields below come from that card, the Hub model API, and the repository’s own config.json when those files exist. A field we cannot source is omitted rather than guessed.

Organisationzai-org
ReleasedRepo creation date on Hugging Face3 Apr 2026
Last modified13 May 2026
ParametersExact, from the safetensors index753.9B 753,864,139,008
Context lengthmax_position_embeddings — architectural maximum, not necessarily served198K 202,752
Licencemit
Pipeline / taskpipeline_tag on the Hugging Face model APItext-generation
File formatssafetensors
Librarylibrary_name on the Hugging Face model APItransformers
Architectureglm_moe_dsa
Layers78
Vocabulary154,880
DownloadsAt last check546.9k
Likes1.8k
GatedNo

How to run

Safetensors weights are on the Hugging Face repository. The parameter count on this page came from that index.

The Hugging Face model API lists the library as transformers.

Load it from huggingface.co/zai-org/GLM-5.1. This page does not add install steps that the Hub files do not state.

Agent capabilities

Derived from the model’s own chat template, with the match counts behind each finding.

  • ●Tool calling16 matches in template
  • ●Reasoning / thinking18 matches in template
  • ●System prompt1 match in template
  • ○Image inputno evidence in template
  • ○Video inputno evidence in template
  • ○Audio inputno evidence in template

Questions this record can answer

When was GLM-5.1 released?
The Hugging Face repository was created on 3 Apr 2026, which is the date this register uses.
How many parameters does GLM-5.1 have?
The safetensors index gives 753,864,139,008 parameters, shown here as 753.9B. That figure is exact, not rounded.
What is the context length of GLM-5.1?
202,752 tokens. That is max_position_embeddings from the model's own config.json — the architectural maximum, not necessarily the context a provider serves.
What licence is GLM-5.1 under?
The Hub card lists mit.
Is GLM-5.1 gated?
No. The Hugging Face model API does not mark this repository as gated.
Does the GLM-5.1 chat template show tool calling?
The chat template contains evidence of tool calling.

Where each field came from

  • Hugging Face model API — releasedAt, lastModified, downloads, likes, task, license, gated, parameters, libraryName, formats. Checked 18 Oct 2026.
  • config.json — contextLength, layers, vocabSize, architecture. Checked 18 Oct 2026.
  • chat template — capabilities. Checked 18 Oct 2026.

First recorded 26 Sept 2026, last checked 18 Oct 2026. This record is compiled automatically from the sources above. Where a field is blank, we could not source it and have not guessed. Canonical repository: huggingface.co/zai-org/GLM-5.1.