Qwen/Qwen3-32B
Qwen/Qwen3-32B is a Qwen 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 32,762,123,264. Architectural context length (max_position_embeddings) is 40,960. The listed licence is apache-2.0. The Hub repository was created on 27 Apr 2025, which is the release date this register uses.
Primary source: the Hugging Face model card for Qwen/Qwen3-32B. 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 | Qwen |
|---|---|
| ReleasedRepo creation date on Hugging Face | 27 Apr 2025 |
| Last modified | 26 Jul 2025 |
| ParametersExact, from the safetensors index | 32.8B 32,762,123,264 |
| Context lengthmax_position_embeddings — architectural maximum, not necessarily served | 40K 40,960 |
| Licence | apache-2.0 |
| Pipeline / taskpipeline_tag on the Hugging Face model API | text-generation |
| File formats | safetensors |
| Architecture | qwen3 |
| Layers | 64 |
| Vocabulary | 151,936 |
| DownloadsAt last check | 4.1m |
| Likes | 754 |
| 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/Qwen/Qwen3-32B. 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 calling23 matches in template
- ●Reasoning / thinking15 matches in template
- ●System prompt3 matches in template
- ○Image inputno evidence in template
- ○Video inputno evidence in template
- ○Audio inputno evidence in template
Questions this record can answer
- When was Qwen3-32B released?
- The Hugging Face repository was created on 27 Apr 2025, which is the date this register uses.
- How many parameters does Qwen3-32B have?
- The safetensors index gives 32,762,123,264 parameters, shown here as 32.8B. That figure is exact, not rounded.
- What is the context length of Qwen3-32B?
- 40,960 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 Qwen3-32B under?
- The Hub card lists apache-2.0.
- Is Qwen3-32B gated?
- No. The Hugging Face model API does not mark this repository as gated.
- Does the Qwen3-32B 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 2 Oct 2026.
- config.json — contextLength, layers, vocabSize, architecture. Checked 2 Oct 2026.
- chat template — capabilities. Checked 2 Oct 2026.
First recorded 24 Sept 2026, last checked 2 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/Qwen/Qwen3-32B.