zai-org/GLM-4.7
zai-org/GLM-4.7 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 358,337,791,296. Architectural context length (max_position_embeddings) is 202,752. The listed licence is mit. The Hub repository was created on 22 Dec 2025, which is the release date this register uses.
Primary source: the Hugging Face model card for zai-org/GLM-4.7. 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.
| Organisation | zai-org |
|---|---|
| ReleasedRepo creation date on Hugging Face | 22 Dec 2025 |
| Last modified | 29 Jan 2026 |
| ParametersExact, from the safetensors index | 358.3B 358,337,791,296 |
| Context lengthmax_position_embeddings — architectural maximum, not necessarily served | 198K 202,752 |
| Licence | mit |
| Pipeline / taskpipeline_tag on the Hugging Face model API | text-generation |
| File formats | safetensors |
| Architecture | glm4_moe |
| Layers | 92 |
| Vocabulary | 151,552 |
| DownloadsAt last check | 106.8k |
| Likes | 2.1k |
| Gated | No |
How to run
Safetensors weights are on the Hugging Face repository. The parameter count on this page came from that index.
Load it from huggingface.co/zai-org/GLM-4.7. 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 calling13 matches in template
- ●Reasoning / thinking16 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-4.7 released?
- The Hugging Face repository was created on 22 Dec 2025, which is the date this register uses.
- How many parameters does GLM-4.7 have?
- The safetensors index gives 358,337,791,296 parameters, shown here as 358.3B. That figure is exact, not rounded.
- What is the context length of GLM-4.7?
- 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-4.7 under?
- The Hub card lists mit.
- Is GLM-4.7 gated?
- No. The Hugging Face model API does not mark this repository as gated.
- Does the GLM-4.7 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. Checked 28 Sept 2026.
- config.json — contextLength, layers, vocabSize, architecture. Checked 28 Sept 2026.
- chat template — capabilities. Checked 28 Sept 2026.
First recorded 24 Sept 2026, last checked 28 Sept 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-4.7.