You're looking at a specific version of this model. Jump to the model overview.
lucataco /qwen3-vl-8b-instruct:39e89366
Input schema
The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.
| Field | Type | Default value | Description |
|---|---|---|---|
| media |
string
|
Optional image or video file. Supported formats: images (jpg, png, etc.) and videos (mp4, avi, mov, etc.).
|
|
| top_p |
number
|
0.9
Max: 1 |
Cumulative probability for nucleus sampling.
|
| prompt |
string
|
Describe what is happening in the media content
|
Instruction or conversation turn for Qwen3-VL.
|
| video_fps |
number
|
1
Min: 0.1 Max: 10 |
Frames per second to sample from video. Only applies to video inputs. Lower values reduce token count.
|
| temperature |
number
|
0.7
Max: 2 |
Sampling temperature; set to 0 for deterministic output.
|
| max_new_tokens |
integer
|
512
Min: 1 Max: 4096 |
Maximum number of new tokens to sample.
|
| video_max_pixels |
integer
|
200704
Max: 1048576 |
Maximum pixels for video frames. Only applies to video inputs. Controls token count. Set to 0 for auto. Recommended: 50176-786432.
|
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{'title': 'Output', 'type': 'string'}