tongyi

Tongyi Deep Research, the Leading Open-source Deep Research Agent

QA-Pilot is an interactive chat project that leverages online/local LLM for rapid understanding and navigation of GitHub code repository.

All-round Creator and Editor

Tongyi Qwen Aliyun Dashscope API Golang implementation, non-official

Run Z-Image-Turbo locally on Apple Silicon (M1/M2/M3/M4) with just two commands. MPS-optimized, Gradio UI, bilingual support.

Wan2.2-Animate-14B动作迁移及视频人物替换软件一键启动整合包

通义灵码vscode插件对话数据导出工具

FunASR最新语音识别模型Fun-ASR-Nano-2512实时识别热词版

🖼️ Enhance images effortlessly by adding or removing objects with the Qwen-Image-Edit-Object-Manipulator, ensuring realism and background detail.

Wan2.2-S2V-14B音频驱动的电影视频生成免安装一键启动整合包

Curriculum Vitae AI Agent 🤖 开箱即用的人工智能求职助手，有针对性的调整简历，助你快速找到心仪的工作。

用阿里通义模型在网站添加一个 AI 助手，可配置本地知识库

Accelerate Qwen3.5 KVCache with TurboQuant MLX-LM tools for prompt caching, quantized attention, and research-ready evals

🎨 Edit images in real-time using the Qwen-Image-Edit-2509 model with up to 20x speed improvements through StreamDiffusion-inspired technology.

简单的数据mock库，0配置随机生成一组各种类型的假数据，支持随机图片、base64、颜色

RAG-powered clothing e-commerce customer service assistant - Streamlit + DashScope + Chroma + Tongyi LLM, glassmorphism chat UI

阿里千问办公（通义千问企业版）的中文说明、答疑与使用指南合集：技能库、定时任务、订阅答疑。内容整理自老手村官网。

Run local LLMs on RTX 3090 hardware with validated configs for vLLM, llama.cpp, and SGLang. Use optimized setups for high throughput or long-context stability.

Build open source deep research agents using multiple models, search tools, and MCP servers.

🚀 Achieve faster Qwen3-0.6B inference with the MegaQwen CUDA megakernel, delivering 531 tok/s decode on RTX 3090—3.9x faster than HuggingFace.