Qwen3.5¶
Class: Qwen35VLBlockV2
Source: inference.core.workflows.core_steps.models.foundation.qwen3_5vl.v2.Qwen35VLBlockV2
This workflow block runs Qwen3.5—a vision language model that accepts an image and an optional text prompt—and returns a text answer based on a conversation template.
Type identifier¶
Use the following identifier in step "type" field: roboflow_core/qwen3_5vl@v2to add the block as
as step in your workflow.
Properties¶
| Name | Type | Description | Refs |
|---|---|---|---|
name |
str |
Enter a unique identifier for this step.. | ❌ |
prompt |
str |
Optional text prompt to provide additional context to Qwen3.5. Otherwise it will just be a default one, which may affect the desired model behavior.. | ❌ |
model_version |
str |
The Qwen3.5 model to be used for inference.. | ✅ |
system_prompt |
str |
Optional system prompt to provide additional context to Qwen3.5.. | ❌ |
max_new_tokens |
int |
Maximum number of tokens to generate. If not set, the model's default will be used.. | ❌ |
The Refs column marks possibility to parametrise the property with dynamic values available
in workflow runtime. See Bindings for more info.
Runtime compatibility¶
-
hard— runtimeself_hosted_cpu; executionlocal - Requires a GPU; run_locally() loads a model that needs CUDA.
Available Connections¶
Compatible Blocks
Check what blocks you can connect to Qwen3.5 in version v2.
- inputs:
Camera Calibration,Polygon Visualization,Stability AI Outpainting,Camera Focus,Halo Visualization,Stability AI Image Generation,Single-Label Classification Model,QR Code Generator,Ellipse Visualization,Image Slicer,Semantic Segmentation Model,Camera Focus,Perspective Correction,Absolute Static Crop,Classification Label Visualization,Bounding Box Visualization,Image Contours,Image Preprocessing,Background Subtraction,Multi-Label Classification Model,Object Detection Model,Multi-Label Classification Model,Pixelate Visualization,Color Visualization,Crop Visualization,Mask Visualization,Stitch Images,Image Slicer,Depth Estimation,Text Display,Contrast Equalization,Relative Static Crop,Icon Visualization,Triangle Visualization,Background Color Visualization,Blur Visualization,Keypoint Detection Model,Corner Visualization,Model Comparison Visualization,SIFT Comparison,Single-Label Classification Model,Grid Visualization,Semantic Segmentation Model,Dot Visualization,Object Detection Model,Line Counter Visualization,Instance Segmentation Model,Reference Path Visualization,Polygon Visualization,Halo Visualization,Stability AI Inpainting,Contrast Enhancement,Image Threshold,Image Convert Grayscale,Trace Visualization,Circle Visualization,Label Visualization,SIFT,Morphological Transformation,Morphological Transformation,Instance Segmentation Model,Polygon Zone Visualization,Image Blur,Keypoint Visualization,Keypoint Detection Model,Heatmap Visualization,Instance Segmentation Model,Dynamic Crop - outputs:
Roboflow Asset Library Attributes,Detections Consensus,Microsoft SQL Server Sink,PLC EthernetIP,Per-Class Confidence Filter,SAM 3
Input and Output Bindings¶
The available connections depend on its binding kinds. Check what binding kinds
Qwen3.5 in version v2 has.
Bindings
-
input
images(image): The image to infer on..model_version(roboflow_model_id): The Qwen3.5 model to be used for inference..
-
output
parsed_output(dictionary): Dictionary.
Example JSON definition of step Qwen3.5 in version v2
{
"name": "<your_step_name_here>",
"type": "roboflow_core/qwen3_5vl@v2",
"images": "$inputs.image",
"prompt": "What is in this image?",
"model_version": "qwen3_5-0.8b",
"system_prompt": "You are a helpful assistant.",
"max_new_tokens": "<block_does_not_provide_example>"
}