Qwen LLM Ecosystem LLM Tools

Tools, implementations, and optimizations specifically for the Qwen/Qwen2/Qwen3 language models across different frameworks and hardware platforms. Does NOT include general LLM tools, other proprietary models, or non-Qwen-specific optimizations.

There are 22 qwen llm ecosystem tools tracked. 2 score above 50 (established tier). The highest-rated is QwenLM/Qwen at 55/100 with 20,703 stars.

Get all 22 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=llm-tools&subcategory=qwen-llm-ecosystem&limit=20"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

#	Tool	Score	Tier	Stars	Language
1	QwenLM/Qwen The official repo of Qwen (通义千问) chat & pretrained large language model...	55	Established	20,703	Python
2	LLM-Red-Team/qwen-free-api 🚀...	51	Established	1,182	TypeScript
3	QwenLM/Qwen-VL The official repo of Qwen-VL (通义千问-VL) chat & pretrained large vision...	45	Emerging	6,569	Python
4	willbnu/Qwen-3.5-16G-Vram-Local Configs, launchers, benchmarks, and tooling for running Qwen3.5 GGUF models...	45	Emerging	21	Python
5	QwenLM/qwen.cpp C++ implementation of Qwen-LM	43	Emerging	619	C++
6	yassa9/qwen600 Static suckless single batch CUDA-only qwen3-0.6B mini inference engine	43	Emerging	546	Cuda
7	BoltzmannEntropy/metalQwen3 Metal GPU implementation of the Qwen3 transformer model on macOS with...	36	Emerging	43	C++
8	yvonwin/qwen2.cpp qwen2 and llama3 cpp implementation	33	Emerging	48	C++
9	lisniuse/qwen-desktop 通义千问非官方桌面端	31	Emerging	3	JavaScript
10	AstraBert/PhiQwenSTEM A reasoning assistant for your STEM education	26	Experimental	24	TypeScript
11	Yash-1335/qwen600 🚀 Build a fast inference engine for the QWEN3-0.6B model using CUDA,...	24	Experimental	—	Cuda
12	ExpertVagabond/purple-squirrel-r1 8B reasoning LLM fine-tuned with DeepSeek-R1 + MLX LoRA on Apple Silicon....	22	Experimental	—	—
13	lf1up/qwen-uncensored-playground QWEN UNCENSORED AI RACE	22	Experimental	—	Jupyter Notebook
14	Jokerdajinbao/Qwen-7B-FastWeb 基于ModelScope社区开源的通意千问Qwen-7B-Chat体验程序修改的Web版本，以方便快速部署体验。	20	Experimental	10	Python
15	shenxiangzhuang/qwen Elixir ❤️ 通义千问	19	Experimental	4	Elixir
16	mrdhnto/qwen-to-lm-studio-conversation A simple PowerShell script to convert exported chat conversations from Qwen...	15	Experimental	1	PowerShell
17	miguefuentes1985/vllm-qwen3.5-nvfp4-5090 Run Qwen3.5-35B MoE model on RTX 5090 with vLLM using NVFP4 quantization for...	14	Experimental	—	Jinja
18	Skeleratis/qwen-chat-ios Run Alibaba’s Qwen large language models locally on iOS for AI chat with...	14	Experimental	—	—
19	suzume-hue/wen-s-mindscape An interactive web application for exploring the psychometric battery...	14	Experimental	—	TypeScript
20	Pogud/MegaQwen 🚀 Achieve faster Qwen3-0.6B inference with the MegaQwen CUDA megakernel,...	13	Experimental	—	Cuda
21	AiGptCode/AI-battle-llama3-vs-qwen2 Welcome to our AI Battle! Ask a question and let our two AI models battle it out	11	Experimental	4	HTML
22	JohnClaw/qwen3.java Java-port of qwen3.c	11	Experimental	2	Java

Comparisons in this category

Qwen and Qwen-VL (55 vs 45) Qwen and qwen-free-api (55 vs 51) Qwen and Qwen-7B-FastWeb (55 vs 20) Qwen and qwen-desktop (55 vs 31) qwen-free-api and Qwen-VL (51 vs 45) qwen-free-api and qwen-desktop (51 vs 31) qwen.cpp and qwen2.cpp (43 vs 33)