nvidia/Qwen3.6-27B-NVFP4
nvidia/Qwen3.6-27B-NVFP4 is a nvidia 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 18,164,649,200. Architectural context length (max_position_embeddings) is 262,144. The listed licence is apache-2.0. The Hub repository was created on 22 Jun 2026, which is the release date this register uses.
Primary source: the Hugging Face model card for nvidia/Qwen3.6-27B-NVFP4. 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 | nvidia |
|---|---|
| ReleasedRepo creation date on Hugging Face | 22 Jun 2026 |
| Last modified | 30 Jun 2026 |
| ParametersExact, from the safetensors index | 18.2B 18,164,649,200 |
| 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-generation |
| Base modelDeclared on the Hub; not a page on this register | Qwen/Qwen3.6-27B |
| File formats | safetensors, NVFP4 |
| Architecture | qwen3_5 |
| Layers | 64 |
| Vocabulary | 248,320 |
| DownloadsAt last check | 910.5k |
| Likes | 445 |
| Gated | No |
Lineage
The Hub card names Qwen/Qwen3.6-27B as the base model. That id is not a page on this register.
How to run
Safetensors weights are on the Hugging Face repository. The parameter count on this page came from that index.
The repository name marks this record as NVFP4.
Load it from huggingface.co/nvidia/Qwen3.6-27B-NVFP4. 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 calling28 matches in template
- ●Reasoning / thinking17 matches in template
- ●System prompt3 matches in template
- ●Image input4 matches in template
- ●Video input4 matches in template
- ○Audio inputno evidence in template
Questions this record can answer
- When was Qwen3.6-27B-NVFP4 released?
- The Hugging Face repository was created on 22 Jun 2026, which is the date this register uses.
- How many parameters does Qwen3.6-27B-NVFP4 have?
- The safetensors index gives 18,164,649,200 parameters, shown here as 18.2B. That figure is exact, not rounded.
- What is the context length of Qwen3.6-27B-NVFP4?
- 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 Qwen3.6-27B-NVFP4 under?
- The Hub card lists apache-2.0.
- Is Qwen3.6-27B-NVFP4 gated?
- No. The Hugging Face model API does not mark this repository as gated.
- Does the Qwen3.6-27B-NVFP4 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 18 Oct 2026.
- config.json — contextLength, layers, vocabSize, architecture. Checked 18 Oct 2026.
- chat template — capabilities. Checked 18 Oct 2026.
First recorded 16 Oct 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/nvidia/Qwen3.6-27B-NVFP4. This page is a quantisation or conversion. It is kept for completeness, excluded from the sitemap, and marked noindex.