Qwen ORG

Qwen3.6 is the large language model series developed by Qwen team, Alibaba Group.

Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

AI model that understands both text and images or video together, letting you ask questions about screenshots, documents, charts, and video content.

Qwen3-Coder is the code version of Qwen3, the large language model series developed by Qwen team.

Qwen3-Coder is an open-weight family of code-focused AI models built for autonomous coding agents, supports a 256K-token context window, 358 programming languages, and runs locally or via API.

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.

Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.

Python framework for building AI agent apps on Qwen LLMs that lets the AI use external tools, run code, search the web, and remember context across a conversation.

Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.

Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.

Qwen3 is a family of open-weight AI language models from Alibaba that can switch between thinking mode for complex reasoning and fast mode for everyday chat, available in sizes from 0.6B to 235B parameters.

An open-source AI coding agent that lives in your terminal.

A terminal-based AI coding assistant that helps you understand, refactor, and generate code by connecting to Qwen or other AI models.

The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.

Alibaba's open-source family of large language models (1.8B, 72B parameters) trained on 3 trillion multilingual tokens, with chat versions for conversation, coding, math, and tool use.

Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice cloning.

Qwen3-TTS is a set of open-source AI text-to-speech models from Alibaba that convert text to natural speech in 10 languages, with voice cloning, text-described voice styles, and streaming output starting in under 100 milliseconds.

The official repo of Qwen-VL (通义千问-VL) chat & pretrained large vision language model proposed by Alibaba Cloud.

Qwen2.5-Omni is an end-to-end multimodal model by Qwen team at Alibaba Cloud, capable of understanding text, audio, vision, video, and performing real-time speech generation.

Qwen3-ASR is an open-source series of ASR models developed by the Qwen team at Alibaba Cloud, supporting stable multilingual speech/music/song recognition, language detection and timestamp prediction.

The official repo of Qwen2-Audio chat & pretrained large audio language model proposed by Alibaba Cloud.

No description.

Qwen-Image-Layered: Layered Decomposition for Inherent Editablity

The official repo of Qwen-Audio (通义千问-Audio) chat & pretrained large audio language model proposed by Alibaba Cloud.

No description.

A series of math-specific large language models of our Qwen2 series.

Official Python toolkit for the Qwen3-ASR API. Parallel high‑throughput calls, robust long‑audio transcription, multi‑sample‑rate support.

C++ implementation of Qwen-LM

The official repository of Qwen-VLA

high-performance linear attention kernel library built on TileLang

QwQ is the reasoning model series developed by Qwen team, Alibaba Cloud.

Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling

Qwen3Guard is a multilingual guardrail model series developed by the Qwen team at Alibaba Cloud.

No description.

Official repository for ACL 2025 paper "ProcessBench: Identifying Process Errors in Mathematical Reasoning"

MCP-based Computer Use service for Qwen Code and any AI agent — controls macOS, Linux, and Windows via accessibility APIs.

A high-throughput and memory-efficient inference and serving engine for LLMs

A collection of practical examples and best practices for Qwen Code

👑 Qwen Blog. Visit https://qwen.ai/research for the latest news.

No description.

No description.

No description.

Implementations of online merging optimizers proposed by Online Merging Optimizers for Boosting Rewards and Mitigating Tax in Alignment

CodeElo: Benchmarking Competition-level Code Generation of LLMs with Human-comparable Elo Ratings

WebWorld is a large-scale web world model that helps train web agents in a simulated browser, avoiding the latency and safety issues of the real web.

[NeurIPS 2025 D&B Track] Evaluation Code Repo for Paper "PolyMath: Evaluating Mathematical Reasoning in Multilingual Contexts"

A high-throughput and memory-efficient inference and serving engine for LLMs

A documentation translation tool specifically designed for Qwen Code

Open-source examples and guides for building with the Qwen. Browse a collection of snippets, advanced techniques and walkthroughs.

No description.

A GitHub Action that integrates Qwen Code into your development workflow.

No description.