# Alibaba's Qwen team releases 4B vision-language model

> The new Qwen3.5-4B model combines text and image understanding in a compact, permissively licensed package for developers.

Published by The Open Weights on Feb 27, 2026. Canonical: https://theopenweights.com/news/qwen3-5-4b-xcb0

## Key facts

- Company: Qwen · Alibaba
- Model: Qwen3.8-27B
- Version: 3.5
- Category: Vision-Language
- Modalities: Text / LLM, Vision-Language
- License: Apache 2.0 (Open weights, commercial use allowed)
- Parameters: 4B
- Context window: 262K tokens
- Architecture: Qwen3_5ForConditionalGeneration
- Precision: BF16
- Weights size: 9.3 GB
- Significance: notable
- Published: 2026-02-27
- Last verified: 2026-06-17
- Hugging Face: https://huggingface.co/Qwen/Qwen3.5-4B
- Canonical URL: https://theopenweights.com/news/qwen3-5-4b-xcb0

The Qwen team at Alibaba has released Qwen3.5-4B, a new 4-billion-parameter model that marks the debut of their Qwen3.5 family. Released under the permissive Apache 2.0 license, the model is designed for instruction-following tasks that involve both text and images.

As a vision-language model (VLM), Qwen3.5-4B can process and understand visual information alongside natural language prompts. This enables applications like describing the content of a photo, answering questions about an image, or following complex instructions that reference visual elements.

The release is notable for its combination of compact size and open access. A 4B parameter count makes the model more accessible for developers and researchers who may not have access to large-scale GPU clusters. Paired with the commercially-friendly license, Qwen3.5-4B represents another strong contender in the growing field of smaller, capable open-source multimodal models.

This release is the first in the Qwen3.5 series, setting the stage for potential future models in the family. Developers can access the model card, weights, and usage examples directly from the official [Hugging Face repository](https://huggingface.co/Qwen/Qwen3.5-4B).

## Get the model

- [Hugging Face](https://huggingface.co/Qwen/Qwen3.5-4B)

## Sources

- [Qwen/Qwen3.5-4B](https://huggingface.co/Qwen/Qwen3.5-4B) — Hugging Face, Feb 27, 2026

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "Alibaba's Qwen team releases 4B vision-language model", The Open Weights, Feb 27, 2026, https://theopenweights.com/news/qwen3-5-4b-xcb0