Qwen/Qwen3.8-27B
Qwen/Qwen3.8-27B is an image text to text model published by Qwen on Hugging Face. At the collection of October 24, 2026 it was No. 10 on the trending list, with 7,710,011 downloads in 30 days and 18,303 likes.
Collected · snapshot shipped with the site build, not a live feed
Why it is on the list
- No. 10 by Hugging Face trending score (314)
- +7 likes since 2026-10-23
- 7,710,011 downloads in the last 30 days
7.71M
18.3K
Since October 23, 2026: +0 downloads (30-day figure), +7 likes
Positions and counts are Hugging Face’s; we report them and add no score of our own.
Source: Hugging Face public API · updated
Fact sheet
- Apache-2.0 · Commercial use allowedPermissive licence: commercial use is allowed, with the attribution and notice conditions of the licence.
- 27,781,427,952 parametersAbout 55.6 GB of weights at 16 bits; about 15.6 GB at a typical 4-bit quantisation.
- safetensors, transformers
- Open download
- ·
- 17,715,784
Most downloaded quantisations
- unsloth/Qwen3.8-27B-GGUF (opens in a new tab)
5.75M downloads in 30 days
- Qwen/Qwen3.8-27B-FP8 (opens in a new tab)
4.25M downloads in 30 days
- lmstudio-community/Qwen3.8-27B-MLX-4bit (opens in a new tab)
3.74M downloads in 30 days
Questions about Qwen3.8-27B
Why is Qwen/Qwen3.8-27B trending?
No. 10 by Hugging Face trending score (314); +7 likes since 2026-10-23; 7,710,011 downloads in the last 30 days. Hugging Face does not publish the formula of its trending score; these are the public figures behind the position.
Can Qwen3.8-27B be used commercially?
The repository is tagged with the licence "Apache-2.0". Permissive licence: commercial use is allowed, with the attribution and notice conditions of the licence. The tag is set by the uploader, so confirm it against the licence file in the repository.
How large is Qwen3.8-27B?
27.8B parameters according to the safetensors metadata. Weights alone take about 56 GB at 16 bits per parameter and about 16 GB in a typical 4-bit quantisation, before the memory needed for the context.
Are there quantised versions of Qwen3.8-27B?
Yes. The most downloaded repositories that declare Qwen/Qwen3.8-27B as their base are unsloth/Qwen3.8-27B-GGUF (5.75M downloads in 30 days), Qwen/Qwen3.8-27B-FP8 (4.25M downloads in 30 days), lmstudio-community/Qwen3.8-27B-MLX-4bit (3.74M downloads in 30 days).