Run a 27B model that reads images and video yourself
A general-purpose model from Alibaba’s Qwen team that handles text, images and video together, with a control for how much it thinks before answering.
At 27 billion parameters it is aimed at people who want to run something capable on their own hardware.
You could use it to…
- Show it a screenshot and ask what broke the dashboard
- Read text, images and video together in one request
- Run a 27B model on your own hardware
Can I use this?
You'll need A high-end GPU, or a hosted service · Setup needed
Worth knowing At full precision a 27-billion-parameter model needs a large amount of graphics memory; compressed versions that fit smaller machines are published separately by other people. The creator says a hosted version is coming but not yet available. Released under Apache 2.0. BuildTube has not run or verified this model.
Why it's here
Getting attention on Hugging Face
- 16,696 people have liked it on Hugging Face.
- It was downloaded 6,950,834 times in the last 30 days.
Numbers from the snapshot taken 1 October 2026; not refreshed since.
Behind it
See the code on Hugging FaceBuildTube has not run or verified this project. Everything above is written from what the creator published.
Made this?