qwen3_vl_single

Model type	qwen3_vl_single
Class	Qwen3VLCausalLMModel
Task	qwen3-vl-vision-language
Source	models/qwen_vl.py

Description

Qwen3-VL vision-language model with packed-attention vision encoder.

Usage

mobius build --model <MODEL_ID> output_dir/

from mobius import build

model = build("<MODEL_ID>")