[GH-ISSUE #9144] Please add support for Omniparser V2 #5949

Open
opened 2026-04-12 17:17:44 -05:00 by GiteaMirror · 0 comments
Owner

Originally created by @Emasoft on GitHub (Feb 15, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9144

Microsoft presented Omniparser V2 and it is showing the best performances in GUI parsing. You can read about the details here.
It is not a multimodal but a visual parsing model specialized in detecting the GUI elements and can be combined with any LLM.

It would be great to add support for Omniparser V2 in Ollama. It would be even better if it were possible to serve both Omniparser and some distilled Deepseek-R1 models at the same time, to serve Computer-Use clients.

https://github.com/microsoft/OmniParser/

Originally created by @Emasoft on GitHub (Feb 15, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9144 Microsoft presented Omniparser V2 and it is showing the best performances in GUI parsing. You can read about the details [here](https://www.microsoft.com/en-us/research/articles/omniparser-v2-turning-any-llm-into-a-computer-use-agent/). It is not a multimodal but a visual parsing model specialized in detecting the GUI elements and can be combined with any LLM. It would be great to add support for Omniparser V2 in Ollama. It would be even better if it were possible to serve both Omniparser and some distilled Deepseek-R1 models at the same time, to serve Computer-Use clients. https://github.com/microsoft/OmniParser/
GiteaMirror added the model label 2026-04-12 17:17:44 -05:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#5949