qwen

A novel Multimodal Large Language Model (MLLM) architecture, designed to structurally align visual and textual embeddings.

Local AI app and inference engine for agents. Run open-weight LLMs locally — private, 100% offline on your computer. Join our Discord: https://discord.com/invite/8wGSsvmg4V

Parallax is a distributed model serving framework that lets you build your own AI cluster anywhere

Research of DeepSeek Engram Architecture based on Qwen-3 and Stable Diffusion series.

Bringing together outstanding artificial intelligence (AI) open source projects from around the world.

GraphGen: Enhancing Supervised Fine-Tuning for LLMs with Knowledge-Driven Synthetic Data Generation

Qwen3.8-27B on a single RTX 3090 with vLLM: ~1,000 tok/s at 64 concurrent (int8 tensor-core GEMMs, fp16 DeltaNet state), ~114 tok/s single-user at default sampling / ~124 greedy (MTP drafts, own-output draft vocab, calibrated int4 lm_head, split-KV verify attention), 150k-262k context; patches, requant scripts, benchmarks

A desktop MCP client designed as a tool unitary utility integration, accelerating AI adoption through the Model Context Protocol (MCP) and enabling cross-vendor LLM API orchestration.

Chat with AI large language models running natively in your browser. Enjoy private, server-free, seamless AI conversations.

An LLM-powered repository agent designed to assist developers and teams in generating documentation and understanding repositories quickly.

从 NLP 到 LLM 的算法全栈教程，在线阅读地址：https://datawhalechina.github.io/base-llm/

Open-source AI browser agent for Chrome and Firefox (monorepo) 🧠

Multimodal RL training framework for diffusion & omni models

MAC (Multi-Agent CAD): A decoupled multi-agent framework for text-to-CAD generation via constrained test-time compute

🎬 Generate images from any camera viewpoint via 3D interactive control. Drag the camera in 3D space or use sliders to set azimuth/elevation/distance, then generate. Built with Three.js + Gradio, bilingual ZH/EN UI.

🚀 Run Codex Mobile Anywhere: Linux, Windows, or Termux on Android 🚀

Deploy any AI model, agent, database, RAG, and pipeline locally or remotely in minutes

🤖✨ChatMLX is a modern, open-source, high-performance chat application for MacOS based on large language models.

🚀🚀🚀A collection of some awesome public projects about Large Language Model(LLM), Vision Language Model(VLM), Vision Language Action(VLA), AI Generated Content(AIGC), the related Datasets and Applications.

Train a 1B LLM with 1T tokens from scratch by personal

Training/Fine-tuning at the speed of light

♾️ Private Agent Fleet with Spec Coding. Each agent gets their own GPU-accelerated desktop. Run Claude, Codex, Gemini and open models on a full private AI Stack ♾️

Verbalized Sampling, a training-free prompting strategy to mitigate mode collapse in LLMs by requesting responses with probabilities. Achieves 2-3x diversity improvement while maintaining quality. Model-agnostic framework with CLI/API for creative writing, synthetic data generation, and dialogue simulation.

Real-time voice assistant — WebRTC streaming, faster-whisper ASR, local LLM, Vui Nano (300M) TTS. OpenAI Realtime API compatible. Voice cloning, barge-in, ~9× realtime on a 4090. Apache 2.0.

Dingo: A Comprehensive AI Data, Model and Application Quality Evaluation Tool

MimikaStudio - A local-first application for macOS (Apple Silicon) + Agentic MCP Support

🐋MindChat（漫谈）：漫谈人生路, 笑对风霜途

Personal Project: MPP-Qwen14B & MPP-Qwen-Next(Multimodal Pipeline Parallel based on Qwen-LM). Support [video/image/multi-image] {sft/conversations}. Don't let the poverty limit your imagination! Train your own 8B/14B LLaVA-training-like MLLM on RTX3090/4090 24GB.

Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2

Awesome-LLM-Eval: a curated list of tools, datasets/benchmark, demos, leaderboard, papers, docs and models, mainly for Evaluation on LLMs. 一个由工具、基准/数据、演示、排行榜和大模型等组成的精选列表，主要面向基础大模型评测，旨在探求生成式AI的技术边界.