> For the complete documentation index, see [llms.txt](https://docs.roboflow.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.roboflow.com/deploy/supported-models/qwen3-5.md).

# Qwen3.5

Qwen3.5 is Alibaba's vision-language model family. It accepts an image and a text prompt and returns a text response. Two pretrained checkpoints are available:

<table data-search="false"><thead><tr><th>Alias</th><th>Parameters</th></tr></thead><tbody><tr><td><code>qwen3_5-0.8b</code></td><td>0.8B</td></tr><tr><td><code>qwen3_5-2b</code></td><td>2B</td></tr></tbody></table>

## Accuracy

Headline vision-language benchmarks (non-thinking mode) from the official model cards ([0.8B](https://huggingface.co/Qwen/Qwen3.5-0.8B), [2B](https://huggingface.co/Qwen/Qwen3.5-2B)):

<table data-header-hidden data-search="false"><thead><tr><th></th><th></th><th></th></tr></thead><tbody><tr><td>Benchmark</td><td><code>qwen3_5-0.8b</code></td><td><code>qwen3_5-2b</code></td></tr><tr><td>MMMU</td><td>47.4</td><td>64.2</td></tr><tr><td>MathVista (mini)</td><td>58.6</td><td>73.9</td></tr><tr><td>MMBench (EN v1.1)</td><td>68.0</td><td>81.3</td></tr></tbody></table>

## Inference speed

Latency measured with [Roboflow Inference](https://inference.roboflow.com/) on 1x NVIDIA L4, batch size 1, generating exactly 128 tokens with greedy decoding from a fixed prompt. Latency scales with output length, so use tokens/sec to estimate other lengths.

<table data-search="false"><thead><tr><th>Alias</th><th>Latency, 128 tokens (ms)</th><th>Tokens/sec</th></tr></thead><tbody><tr><td><code>qwen3_5-0.8b</code></td><td>3307</td><td>39</td></tr><tr><td><code>qwen3_5-2b</code></td><td>3688</td><td>35</td></tr></tbody></table>

## Using Qwen 3.5 VL via Workflows

Qwen 3.5 VL is available as a preconfigured [Workflow](/workflows/what-is-workflows.md) on the "Open-Source Models" tab of the Models page. Select "Qwen VL", choose a model variant and prompt, then click "Test API" to fork the Workflow into your Workspace and start running inference.

The Workflow uses the unified `qwen_vlm@v1` block, which supports multiple Qwen VL generations:

<table data-search="false"><thead><tr><th>Model</th><th>Parameters</th></tr></thead><tbody><tr><td>Qwen 3.5 VL 0.8B</td><td>0.8B</td></tr><tr><td>Qwen 3.5 VL 2B</td><td>2B</td></tr><tr><td>Qwen 3 VL 2B</td><td>2B</td></tr><tr><td>Qwen 2.5 VL 7B</td><td>7B</td></tr></tbody></table>

## Using Qwen 3.5 VL via Inference SDK

{% hint style="info" %}
Direct Inference SDK calls to Qwen3.5 require a [Dedicated Deployment](/deploy/dedicated-deployments.md) or [self-hosted Inference](https://inference.roboflow.com/). For hosted access, use the Workflow path described above.
{% endhint %}

{% stepper %}
{% step %}

### Get your API Key

Create a Roboflow account, find your key on the [Roboflow API settings page](https://app.roboflow.com/settings/api) and make it available to your shell:

```bash
export ROBOFLOW_API_KEY="your-key-here"
```

{% endstep %}

{% step %}

### Install the dependencies

Install the [Inference SDK](https://inference.roboflow.com/):

```bash
pip install inference-sdk
```

{% endstep %}

{% step %}

### Run the model

Set `api_url` to your Dedicated Deployment URL or a local Inference server.

```python
import os
import cv2
import numpy as np
import requests
from inference_sdk import InferenceHTTPClient

content = requests.get("https://media.roboflow.com/quickstart/dog.jpeg").content
image = cv2.imdecode(np.frombuffer(content, np.uint8), cv2.IMREAD_COLOR)

client = InferenceHTTPClient(
    api_url="https://your-deployment.roboflow.cloud",
    api_key=os.environ["ROBOFLOW_API_KEY"],
)
result = client.infer_lmm(
    image,
    model_id="qwen3_5-2b",
    prompt="Describe this image briefly.",
    max_new_tokens=256,
)
print(result["response"])
```

{% endstep %}
{% endstepper %}

The code above prints the model response to the terminal:

```
A person wearing a white t-shirt and red shorts is carrying a black backpack on their shoulder, with a beagle dog perched on top of it. The scene takes place outdoors in a residential area, with modern apartment buildings in the background and greenery along the sidewalk. The person appears to be walking or standing near a building with large windows.
```

<figure><img src="/files/aLkkibYejlPj2rBeQ3z6" alt=""><figcaption></figcaption></figure>

{% hint style="info" %}
Set `api_url` to match your deployment target:

* `http://localhost:9001` for a local [Inference](https://inference.roboflow.com/) server.
* Your [Dedicated Deployment](/deploy/dedicated-deployments.md) URL for a private endpoint.
  {% endhint %}

You can train your own Qwen3.5 checkpoint on Roboflow and call it by its per-model `{workspace}/{model-slug}` ID (see [Versions, Trainings, and Models](/train/versions-trainings-and-models.md)).

{% embed url="<https://www.youtube.com/watch?v=Y8CR6IzLDaw>" %}