Junyang Lin

Qwen just released the Qwen3.5 Small Model Series — 0.8B, 2B, 4B and 9B. Native multimodal with improved architecture and scaled RL. 0.8B and 2B are tiny and fast for edge devices, 4B makes a strong lightweight agent base, and 9B is already closing the gap with much larger models. Base versions released too.

An open-weight, native vision-language model built for long-horizon agentic tasks. Its hybrid architecture (linear attention + MoE) delivers the capabilities of a 397B giant with the inference speed of a 17B model.

A family of SOTA speech models (0.6B & 1.7B) supporting 10 languages. Features prompt-based Voice Design, 3s zero-shot cloning, and extreme low-latency streaming.

Qwen-Image-2512 is the new open-source SOTA for text-to-image generation. It delivers drastically improved photorealism, finer natural details, and superior text rendering.

Qwen-Image-Layered decomposes images into transparent RGBA layers, unlocking inherent editability. You can move, resize, or delete objects without artifacts. Supports recursive decomposition and variable layer counts.

Qwen3-VL is the new flagship vision-language model from the Qwen team, excelling at visual agent tasks, long-video understanding, and spatial reasoning with a native 256K context window.

Qwen3-omni is a natively end-to-end, omni-modal LLM developed by the Qwen team at Alibaba Cloud, capable of understanding text, audio, images, and video, as well as generating speech in real time.

Qwen3-Next is a new family of models from the Qwen team, featuring a novel architecture that activates just 3B of its 80B parameters. This delivers performance comparable to much larger models with a >10x speedup, especially on long-context tasks.

Qwen3-ASR is a new high-accuracy speech recognition model. It supports 11 languages, excels at transcribing songs with background music, and features a unique contextual biasing system that accepts any text format to improve accuracy on specific terms.

Qwen Chat can now directly read and process the content of any web page when you simply paste a link into the chat.

Built on 20B Qwen-Image, it brings precise bilingual text editing (Chinese & English) while preserving style, and supports both semantic and appearance-level editing.

Qwen-Image-Edit is the editing version of the 20B Qwen-Image model. It offers precise, model-native editing, including bilingual text modification and both high-level semantic and low-level appearance changes.

Qwen-Image is a new 20B open-source image foundation model by the Qwen team. It excels at complex text rendering (especially Chinese) and precise image editing, while also delivering strong general image generation. Available now in Qwen Chat.

Qwen3-235B-A22B-Thinking-2507 is a powerful open-source MoE model (22B active) built for deep reasoning. It achieves SOTA results on agentic tasks, supports a 256K context, and is available on Hugging Face and via API.

Qwen3-Coder is a new 480B MoE open model (35B active) by the Qwen team, built for agentic coding. It achieves SOTA results on benchmarks like SWE-bench, supports up to 1M context, and comes with an open-source CLI tool, Qwen Code.

Qwen Chat for Desktop is here! 💻 All the power of Qwen Chat — now with MCP support for smarter, faster agents. ⚡️ Run MCP Server, boost productivity, and stay in control.

Qwen3 is the newest family of open-weight LLMs (0.6B to 235B MoE) from Alibaba. Features switchable "Thinking Mode" for reasoning vs. speed. Strong performance on code/math. Multilingual.

Your free personal AI assistant for iOS/Android. Powered by Qwen models (inc. QwQ reasoning) for deep thinking, search, multimodal understanding, writing & image gen.

Qwen2.5-Omni is an end-to-end multimodal model by Qwen team at Alibaba Cloud, Understands text, images, audio & video; generates text & natural streaming speech.

Qwen2.5-VL-32B is the open-source 32B vision-language model. Combines strong language understanding with image/video analysis. Optimized with RL.