LBS-27B
LBS-27B is an agentic vision-language model based on Qwen3.8-27b. It uses adaptive image-region inspection learned from synthetic GUI-grounding data and is released as a checkpoint.
What it does
Use it for visual question answering, high-resolution image perception, and GUI grounding.
- Availability
- Released checkpoint available as inclusionAI/LBS-27B
- Pricing model
- Not established
- Deployment
- Serve the checkpoint in a compatible vLLM environment
- Privacy
- Not established
- Licence
- Apache 2.0 for model weights and project software
Capability
Modality
Access
Deployment
Pricing
Target user
Evidence
6 claims- LBS-27B can request up to two independent crops per turn, with a total budget of three crop calls per episode. [1]
with a total budget of three crop calls per episode.
Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights. - The model uses an observation policy learned from synthetic GUI grounding data for visual question answering. [1]
- The released checkpoint is available as inclusionAI/LBS-27B. [1]
More result visualizations are available in the [LBS project](https://github.com/inclusionAI/UI-Venus/tree/LBS);
Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights. - The checkpoint can be served in a compatible vLLM environment. [1]
Serve the released checkpoint in a compatible vLLM environment.
Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights. - LBS-27B scored 89.13% on HR-Bench 4K using strict option matching. [1]
| HR-Bench 4K | 800 | Strict option matching | **89.13** |
Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights. - Operating a live application requires a separate executor. [1]
Grounding predicts a location; operating a live application requires a separate
Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights.
Sources
1
1
Hugging FaceOwner-controlled
https://huggingface.co/inclusionAI/LBS-27B
Retrieved 2026-10-29 00:21 UTC
Verified
Versions
2| Version | Effective | Change | Changed fields | State |
|---|---|---|---|---|
| 2 | 2026-10-29 00:21 UTC | material change | capability, access, availability, deployment | Current |
| 1 | 2026-10-27 00:11 UTC | publication | None | Current |
In briefs
1- Create expressive speech from a short voice sample Daily brief 2026-10-27
Original catalog content is licensed under CC BY 4.0, attributed to wowsuchai. Source quotations and linked content keep their original rights.