Qwen: open-source projects on GitHub
106 repositories on Qwen, picked by the REDDYX AI agent. Each has a summary, key features and a breakdown. Sorted by stars.
// RELATED TOPICS
Ollama: Local LLMs
Run language models (Kimi‑K2.5, DeepSeek, Qwen, Gemma, etc.) locally on your device — simply and quickly.
★ 171,194 · Go🤗 Transformers
A framework for defining machine learning models in text, vision, audio, and multimodal models, for inference and training.
★ 160,482 · PythonONE GATEWAY — 375 AI PROVIDERS
OmniRoute — free MIT gateway with one endpoint to 375 providers (150+ free) and 1400+ models. Supports Claude Code, Cursor, Copilot. Quota-aware fallback and RTK+Caveman
★ 87,451 · TypeScriptHigh-performance LLM engine
A high-performance and memory-efficient engine for inference and serving large language models.
★ 79,783 · PythonLlamaFactory: Unified LLM Tuning
LlamaFactory offers a unified library for efficient fine‑tuning of 100+ LLMs and VLMs, with support for LoRA, QLoRA and distributed multi‑GPU training.
★ 71,186 · PythonWeb UI for Model Training
A simple web interface to train and run open language models (Gemma 4, Qwen3.6, DeepSeek, GPT‑OSS) locally, leveraging efficient fine‑tuning techniques.
★ 64,107 · PythonCowAgent AI Assistant
CowAgent — an ultra‑lightweight AI assistant with task planning, OS and external resource access, and support for many messengers and models.
★ 44,355 · PythonChatBot on LangChain
A local RAG application on LangChain for working with LLMs (ChatGLM, Qwen, Llama) with agent support and loading of custom knowledge.
★ 38,014 · PythonQWEN-CODE: AI CODER IN TERMINAL
An open AI agent for programming, working directly in your terminal and written in TypeScript.
★ 30,510 · TypeScriptFastGPT Knowledge Base
Platform for quickly creating question-answer systems based on LLM with ready data processing, RAG search, and visual workflow orchestration.
★ 28,017 · TypeScriptSGLang: LLM Framework
SGLang is a high-performance framework for serving large language and multimodal models.
★ 27,854 · PythonLocal AI Builder
Open-source local AI application builder for advanced users, an alternative to v0, Lovable, Replit, and Bolt.
★ 20,331 · TypeScriptTWONE YOURSELF IN CHAT
Fine-tune LLM on your chats and bring a digital copy of yourself to life in any chatbot.
★ 18,406 · PythonFreeToken: Local Model Run
FreeToken lets you run large AI models on your PC, delivering data‑center‑class speed and efficiency without needing cloud resources.
★ 17,197 · PythonChatbot Interface
Graphical interface for working with ChatGPT API and other LLMs: support for agents, file Q&A, fine‑tuning and web search.
★ 15,339 · PythonAI Expert Collection
Over 211 AI specialists optimized for 16 tools and 18 departments, with unique agents for the Chinese market.
★ 10,617 · ShellAI Code Without Limits
Endless free AI coding: connect any IDE to Claude/GPT/Gemini via 40+ providers with auto‑fallback and 40% token savings.
★ 9,759 · JavaScriptOUMI EASY LLM TUNING
OUMI lets you quickly fine‑tune (SFT/RL), evaluate, and deploy Qwen, Gemma, and any open agentic LLM/VLM without extra complexity.
★ 9,433 · PythonXINFERENCE - ANY LLM ONE LINE
Replace GPT with any open model by changing just one line of code. Run LLM, multimodal, and speech models via a single production-ready API.
★ 9,318 · PythonNOI - LESS CHAOS, MORE FLOW
Noi is a TypeScript framework that simplifies workflows, removing noise and boosting development productivity.
★ 9,074 · TypeScriptAI partner for 300+ models
ForgeCode is an AI coding assistant that works with Claude, GPT, O Series, Grok, Deepseek, Gemini, and over 300 models.
★ 7,297 · RustVLM-R1: Smart Image Recognition
The project demonstrates how reinforcement learning improves image understanding by multimedia models.
★ 6,046 · Pythontiny-llm - BUILD MINI LLM M1
Course on deploying LLM on Apple Silicon: build your own tiny vLLM + Qwen in just minutes.
★ 5,744 · PythonUltraRAG: RAG pipeline framework
Low-code MCP framework for creating complex and innovative RAG pipelines.
★ 5,549 · PythonEASYR1: MULTIMODAL RL TRAINING
EasyR1 is a scalable framework for multimodal reinforcement learning training on veRL, delivering high efficiency and ease of use.
★ 5,215 · PythonGPU cluster manager
Management of GPU clusters with automatic configuration and orchestration of inference engines (vLLM, SGLang) for high-performance deployment of AI models.
★ 5,041 · PythonVLMEvalKit - TOP TOOL FOR MODEL EVALUATION
Open tool for evaluating multimodal models. Supports 220+ LMM and 80+ benchmarks.
★ 4,492 · PythonLemonade SDK
Lemonade helps users run local AI applications by optimizing LLM performance on their GPU and NPU. Join our Discord!
★ 4,059 · C++SIDEKICK: LOCAL AI CHAT
Sidekick — native macOS app for chatting with a local LLM, pulling answers from files, folders and web pages. Works fully offline on llama.cpp, no external APIs. Supports
★ 3,324 · SwiftHyperQwen: Qwen on Consumer GPUs
The project optimizes running large Qwen models on available GPUs using vLLM patches and requantization. It achieves 127 tokens/s on 24 GB.
★ 2,713 · PythonMTPLX SUPERFAST LAUNCH
MTPLX lets you run Qwen 3.8 Flash Next and Qwen 3.8 27B on Mac at 125 tokens/sec in OpenCode. Thanks to MTP speculative decoding on Apple Silicon, results stay accurate a
★ 2,706 · PythonLocal Claude Code
Run Claude Code entirely on-device with Apple Silicon using an MLX-native server compatible with the Anthropic API. Supports local Qwen 3.5 122B, Llama 3.3 70B, and Gemma
★ 2,578 · PythonAI Short Drama Skill Packs
Curated agent skills for AI short drama creation: screenwriting, storyboarding, and video prompts for Seedance, Kling, MiniMax.
★ 2,321 · HTMLFast Local AI Engine
Rapid-MLX is the fastest local AI engine for Apple Silicon, running 4.2× faster than Ollama and providing a cached first-token time of just 0.08s.
★ 2,185 · PythonLucebox Hub
High-speed server for running LLM locally on consumer hardware. Written in C++ for maximum performance.
★ 2,167 · C++LOCAL OPEN-SOURCE AI AGENT
Atomic-Chat is a private AI engine for running LLM locally without internet, fully offline on your computer. ⭐ 967 stars on GitHub.
★ 2,008 · TypeScriptBEST LLM SKILLS COLLECTION
Curated list of skills and tools for AI agents working with Claude Code, Codex, and Gemini CLI.
★ 1,865 · PythonAPIPARK AI GATEWAY NEW GENERATION
APIPark — gateway for all models: single entry, LLM request management, load balancing and failover. Supports OpenAI, Claude, Gemini, DeepSeek and more, giving unified re
★ 1,826 · TypeScriptSGLANG-OMNI: OMNI-SERVICE FOR AI
SGLang-Omni provides high-performance execution of TTS, ASR, and speech omni-models on Python.
★ 1,791 · PythonOVIS: Visual-Text Sync
A modern MLLM architecture for structural alignment of visual and text embeddings.
★ 1,539 · PythonOpenMed AI for Healthcare
OpenMed is an open-source Python project using AI for medical data analysis and clinical decision support.
★ 1,365 · PythonFAST LAUNCH QWEN3.8 ON AMD
The project provides scripts for instant deployment of Qwen3.8-Flash-Next on AMD Strix Halo (gfx1151) GPU via HIP. All dependencies are built automatically, and inference
★ 1,349 · ShellPARALLAX: BUILD AI CLUSTER
Parallax lets you quickly deploy a distributed inference service on any infrastructure.
★ 1,301 · PythonANGELSLIM: COMPRESSING MODELS WITHOUT LOSS
A tool for model compression focusing on convenience and efficiency. 1257 stars on GitHub.
★ 1,257 · PythonGRAPHGEN: DATA SYNTHESIS FROM GRAPHS
GraphGen creates synthetic data for LLM fine-tuning from knowledge graphs. Integrated with LlamaFactory, it uses structured knowledge to generate quality samples. 1231 Gi
★ 1,234 · PythonCode Agent for LLM
Code agent, optimized for smaller LLMs.
★ 1,083 · TypeScriptMULTI-AGENT CAD 3D GENERATOR
A framework for generating CAD models from natural‑language text using multi‑agent collaboration and bounded test computation.
★ 1,081 · PythonRUN LARGE LLMS LOCALLY
PolyStrata runs Qwen3.8-Flash, GLM 5.3 Flash, DeepSeek V4 and more on your PC. One-click install for Windows and Linux with OpenAI/Anthropic API on localhost.
★ 1,037 · C++Ultra-fast engine
Ultra-fast LLM inference engine in Python with maximum performance. 943 stars on GitHub.
★ 943 · PythonHAPPIER — Universal AI Client
Cross-platform client for working with Codex, Claude Code, Kimi and other AI agents, providing full end-to-end encryption.
★ 867 · TypeScriptBIGMOEONEDGE - SUPER MOE ON PHONE
The project enables running 284 B Mixture‑of‑Experts models on a device with 12 GB of RAM, using only CPU and llama.cpp without loss of accuracy.
★ 855 · C++LLM ON PS5: LLAMA.CPP NATIVELY
PS5LM ports llama.cpp to jailbroken PlayStation 5. Runs any GGUF models natively on console, including Qwen 3.8. 668 stars on GitHub, written in C++.
★ 846 · C++HELIX: Private AI Agent Fleet
Flagship fleet of AI agents, each gets its own GPU-accelerated desktop. Claude, Codex, Gemini on a private stack.
★ 831 · GoRISC-V CPU COMPILED INTO QWEN3.5 WEIGHTS
Qwen3.5-4B with a 32-bit RISC-V CPU compiled directly into model weights. CPU uses Gated DeltaNet state as RAM and executes code inside model forward pass.
★ 814 · PythonFREE TPU FOR QWEN3.8-27B
The kaggle-tpu-lab project runs Qwen3.8-27B (bf16) on a free Kaggle TPU, providing an OpenAI‑compatible API. It supports a 262k token context and ~130 tokens/s speed, wor
★ 801 · PythonSURROGATE — POWERFUL FINE-TUNING IN C++
Training and fine-tuning models at the speed of light. 796 stars on GitHub.
★ 796 · C++DINGO: AI MODEL EVALUATION
Dingo is a tool for comprehensive evaluation of data, model, and AI application quality in Python. It enables measuring reliability and performance of systems.
★ 768 · PythonCODESEEK - SMART CODE SEARCH
A Rust CLI for building function call graphs and hybrid semantic code search across 7 languages. Includes ready‑to‑use MCP tools for Claude Code and Codex CLI.
★ 762 · RustPEGAINFER: Rust + CUDA Infer
Pure Rust LLM engine with CUDA acceleration, OpenAI API compatible, runs Qwen3 and Kimi‑K2 without PyTorch.
★ 742 · RustTENSORSHARP - POWERFUL .NET LLM
A library for quickly launching GGUF models on .NET with GPU support, console app, web chat, and an API compatible with Ollama and OpenAI.
★ 679 · C#New projects on this topic in Telegram
Telegram →