Start the server:

Start the server: Dense: mistralrs serve multimodal -p 1234 -m Qwen/Qwen3.5-27B MoE: mistralrs serve multimodal -p 1234 -m Qwen/Qwen3.5-35B-A3B

"""
Start the server:
    Dense:  mistralrs serve multimodal -p 1234 -m Qwen/Qwen3.5-27B
    MoE:    mistralrs serve multimodal -p 1234 -m Qwen/Qwen3.5-35B-A3B
"""

from openai import OpenAI

client = OpenAI(api_key="foobar", base_url="http://localhost:1234/v1/")

completion = client.chat.completions.create(
    model="default",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://www.garden-treasures.com/cdn/shop/products/IMG_6245.jpg"
                    },
                },
                {
                    "type": "text",
                    "text": "What type of flower is this? Give some fun facts.",
                },
            ],
        },
    ],
    max_tokens=256,
    frequency_penalty=1.0,
    top_p=0.1,
    temperature=0,
)
resp = completion.choices[0].message.content
print(resp)

Source: examples/server/qwen3_5.py