DIEM
About this model
Qwen3 VL 30B A3B is Alibaba's vision-language model from the Qwen3-VL series, offered here inside a Trusted Execution Environment so the deployment can be independently verified via hardware attestation. It accepts images, text, and video, outputting text for tasks like multi-image reasoning, document understanding, and grounded multimodal dialogue. The "A3B" denotes a Mixture-of-Experts design where only about 3B of the 30B parameters activate per token, favoring efficient inference.
Within the Qwen3-VL family, the larger sibling Qwen3 VL 235B scales the same architecture to 235B total parameters with more active experts, while this 30B variant targets lighter deployment with a 128K context window. Compared with the text-only Qwen3 30B A3B, which shares the same MoE backbone and active-parameter budget, this VL edition adds a vision encoder and video processing, letting users configure separate pixel budgets for image and video inputs.
The model is distributed openly on Hugging Face under Apache-2.0, and runs on common serving stacks such as vLLM. Here it is paired with capabilities including function calling, web search, and end-to-end-encrypted, attestable execution. For specific benchmark figures, consult Alibaba's official Qwen3-VL materials, since independently verified scores for this exact configuration are not reproduced above.
This About section is AI-generated from public sources (Claude Opus 4.8), with no human editing. It may contain inaccuracies — verify critical details against the sources listed above.
Research & Papers
4 reference papers linked from the HuggingFace model card.
Qwen3 Technical Report(2025)
An Yang, Anfeng Li, Baosong Yang et al.
In this work, we present Qwen3, the latest version of the Qwen model family. Qwen3 comprises a series of large language models (LLMs) designed to advance performance, efficiency, and multilingual capabilities. The Qwen3 series includes models of both dense and Mixture-of-Expert…
Qwen2.5-VL Technical Report(2025)
We introduce Qwen2.5-VL, the latest flagship model of Qwen vision-language series, which demonstrates significant advancements in both foundational capabilities and innovative functionalities. Qwen2.5-VL achieves a major leap forward in understanding and interacting with the…
Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution(2024)
Peng Wang, Shuai Bai, Sinan Tan et al.
We present the Qwen2-VL Series, an advanced upgrade of the previous Qwen-VL models that redefines the conventional predetermined-resolution approach in visual processing. Qwen2-VL introduces the Naive Dynamic Resolution mechanism, which enables the model to dynamically process…
Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond(2023)
Jinze Bai, Shuai Bai, Shusheng Yang et al.
In this work, we introduce the Qwen-VL series, a set of large-scale vision-language models (LVLMs) designed to perceive and understand both texts and images. Starting from the Qwen-LM as a foundation, we endow it with visual capacity by the meticulously designed (i) visual…
Data sources: Venice API · HuggingFace · Wikipedia · arXiv — enrichment updated 1d ago