Add Qwen3.6 to documentation#4247
Conversation
| ::: | ||
| :::{tab-item} Qwen3.6-35B-A3B | ||
| :sync: Qwen3.6-35B-A3B | ||
| Vision Language MoE model (35B total / 3B active parameters). Requires OpenVINO 2026.2 or newer and enough host memory to fit the INT4 weights. |
There was a problem hiding this comment.
can you make is more specific? also weights is not enough because KV cache needs to be allocated and image embeddings can consume extra RAM. Minumum 21GB VRAM plus KV cache for text generation and image processing embeddings depending on the resolution and image count.
We could add like tested on PantherLake iGPU with 32GB RAM and iGPU allocation increased and B70 dGPU.
mzegla
left a comment
There was a problem hiding this comment.
Approving, but take a look at the comments. Not sure if it;s fine to keep weekly tags and 2026.1 links
| > **Note**: Image source: [Link](https://images.pexels.com/photos/20015887/pexels-photo-20015887.jpeg) | ||
|
|
||
| ```bat | ||
| python openai_agent.py --query "What is the current weather in location depicted in the image?" --image https://raw.githubusercontent.com/openvinotoolkit/model_server/refs/heads/releases/2026/1/demos/continuous_batching/agentic_ai/photo.jpeg --model OpenVINO/Qwen3.6-35B-A3B-int4-ov --base-url http://localhost:8000/v3 --mcp-server-url http://localhost:8080/sse --mcp-server weather |
There was a problem hiding this comment.
to be addressed in another pr
| Pull and start OVMS: | ||
| ```bash | ||
| mkdir -p ${HOME}/models | ||
| docker run -d --user $(id -u):$(id -g) --rm -p 8000:8000 -v ${HOME}/models:/models openvino/model_server:weekly \ |
There was a problem hiding this comment.
to be addressed in another pr
| > **Note**: Image source: [Link](https://images.pexels.com/photos/20015887/pexels-photo-20015887.jpeg) | ||
|
|
||
| ```bash | ||
| python openai_agent.py --query "What is the current weather in location depicted in the image?" --image https://raw.githubusercontent.com/openvinotoolkit/model_server/refs/heads/releases/2026/1/demos/continuous_batching/agentic_ai/photo.jpeg --model OpenVINO/Qwen3.6-35B-A3B-int4-ov --base-url http://localhost:8000/v3 --mcp-server-url http://localhost:8080/sse --mcp-server weather |
There was a problem hiding this comment.
to be addressed in another pr
| Pull and start OVMS: | ||
| ```bash | ||
| mkdir -p ${HOME}/models | ||
| docker run -d --user $(id -u):$(id -g) --rm -p 8000:8000 -v ${HOME}/models:/models --device /dev/dri --group-add=$(stat -c "%g" /dev/dri/render* | head -n 1) openvino/model_server:weekly \ |
There was a problem hiding this comment.
to be addressed in another pr
| > **Note**: Image source: [Link](https://images.pexels.com/photos/20015887/pexels-photo-20015887.jpeg) | ||
|
|
||
| ```bash | ||
| python openai_agent.py --query "What is the current weather in location depicted in the image?" --image https://raw.githubusercontent.com/openvinotoolkit/model_server/refs/heads/releases/2026/1/demos/continuous_batching/agentic_ai/photo.jpeg --model OpenVINO/Qwen3.6-35B-A3B-int4-ov --base-url http://localhost:8000/v3 --mcp-server-url http://localhost:8080/sse --mcp-server weather |
There was a problem hiding this comment.
to be addressed in another pr
🛠 Summary
JIRA/Issue if applicable.
Describe the changes.
🧪 Checklist
``