[GH-ISSUE #13653] Request: Add Qwen3-VL-Embedding Series (Multimodal Embeddings) to Ollama #34735

Closed
opened 2026-04-22 18:33:45 -05:00 by GiteaMirror · 0 comments
Owner

Originally created by @minghua-123 on GitHub (Jan 9, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/13653

Hi Ollama Maintainers & Community,
I’d like to propose adding the Qwen3-VL-Embedding​ family (specifically Qwen3-VL-Embedding-8B and Qwen3-VL-Embedding-2B) to Ollama’s model repository. These embeddings are purpose-built to accept multiple input forms—including text, images, screenshots, and videos, as well as any combination of these modalities in mixed inputs—and would expand Ollama’s multimodal capabilities for local AI workflows.
The model address is as follows:
Qwen3-VL-Embedding-8B
Qwen3-VL-Embedding-2B

Originally created by @minghua-123 on GitHub (Jan 9, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/13653 Hi Ollama Maintainers & Community, I’d like to propose adding the Qwen3-VL-Embedding​ family (specifically Qwen3-VL-Embedding-8B and Qwen3-VL-Embedding-2B) to Ollama’s model repository. These embeddings are purpose-built to accept multiple input forms—including text, images, screenshots, and videos, as well as any combination of these modalities in mixed inputs—and would expand Ollama’s multimodal capabilities for local AI workflows. The model address is as follows: [Qwen3-VL-Embedding-8B](https://huggingface.co/Qwen/Qwen3-VL-Embedding-8B) [Qwen3-VL-Embedding-2B](https://huggingface.co/Qwen/Qwen3-VL-Embedding-2B)
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#34735