autotrust/GEV-26B-Decide
autotrust/GEV-26B-Decide is a autotrust record on this register. The Hugging Face model API lists the pipeline tag as text-classification. The safetensors index gives an exact parameter count of 25,805,936,206. Architectural context length (max_position_embeddings) is 262,144. The listed licence is apache-2.0. The Hub repository was created on 2 Oct 2026, which is the release date this register uses.
Primary source: the Hugging Face model card for autotrust/GEV-26B-Decide. 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 | autotrust |
|---|---|
| ReleasedRepo creation date on Hugging Face | 2 Oct 2026 |
| Last modified | 3 Oct 2026 |
| ParametersExact, from the safetensors index | 25.8B 25,805,936,206 |
| Context lengthmax_position_embeddings — architectural maximum, not necessarily served | 256K 262,144 |
| Licence | apache-2.0 |
| Pipeline / taskpipeline_tag on the Hugging Face model API | text-classification |
| File formats | safetensors |
| Architecture | gemma4 |
| Layers | 30 |
| Vocabulary | 262,144 |
| DownloadsAt last check | 909.8k |
| 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/autotrust/GEV-26B-Decide. 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 calling19 matches in template
- ●Reasoning / thinking5 matches in template
- ●System prompt2 matches in template
- ●Image input6 matches in template
- ●Video input4 matches in template
- ●Audio input4 matches in template
Questions this record can answer
- When was GEV-26B-Decide released?
- The Hugging Face repository was created on 2 Oct 2026, which is the date this register uses.
- How many parameters does GEV-26B-Decide have?
- The safetensors index gives 25,805,936,206 parameters, shown here as 25.8B. That figure is exact, not rounded.
- What is the context length of GEV-26B-Decide?
- 262,144 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 GEV-26B-Decide under?
- The Hub card lists apache-2.0.
- Is GEV-26B-Decide gated?
- No. The Hugging Face model API does not mark this repository as gated.
- Does the GEV-26B-Decide 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 9 Oct 2026.
- config.json — contextLength, layers, vocabSize, architecture. Checked 9 Oct 2026.
- chat template — capabilities. Checked 9 Oct 2026.
First recorded 5 Oct 2026, last checked 9 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/autotrust/GEV-26B-Decide.