Qwen3: open-source projects on GitHub
30 repositories on Qwen3, picked by the REDDYX AI agent. Each has a summary, key features and a breakdown. Sorted by stars.
// RELATED TOPICS
High-performance LLM engine
A high-performance and memory-efficient engine for inference and serving large language models.
★ 79,783 · PythonAI Productivity On-Device
A universal AI productivity tool that runs locally and guarantees complete privacy without complex setup.
★ 59,922 · JavaScriptms-swift: LLM training
A framework for fine-tuning 600+ language and 300+ multimodal models. Supports PEFT, full fine-tuning, CPT/SFT/DPO/GRPO.
★ 14,178 · PythonGENIEX: LLMs on Devices
Run cutting-edge multimodal models on GPU, NPU, and CPU — from PC to mobile and IoT devices.
★ 8,530 · RustDEEP SEARCHER AI AGENT
Deep‑searcher is an open‑source Python framework for deep research of private data. It offers an alternative to Reason and Search with agentic RAG, supporting Claude and
★ 8,395 · PythonNEXA-SDK AI Everywhere Always
Run cutting‑edge LLMs and VLMs on GPU, NPU, and CPU — from PC to mobile and IoT devices. Support for models like GPT‑OSS, Granite‑4, Qwen‑3‑VL, and more.
★ 8,094 · RustSIDEKICK: 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 · PythonPAPERSGPT — AI for Zotero
Powerful AI plugin for Zotero with support for ChatGPT, Gemini, Claude, DeepSeek and other models. 2459 stars!
★ 2,709 · JavaScriptWHISPERJAV NOISE-FREE SUBTITLES
Subtitle generator for video based on Qwen3‑ASR, Whisper, and local LLM, noise-resistant and ideal for JAV content.
★ 2,465 · PythonVOICE ASSISTANT FOR MAC
Wally lets you control Mac by voice and search local documents offline without internet. It runs on Apple Silicon M1 using an on-device offline LLM via llama.cpp and RAG
★ 1,571 · C++RCLI — Voice AI
Voice AI with RAG, no cloud: chat with Mac and request documents locally.
★ 1,507 · C++FAST 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 · ShellRUN 284B LLM ON CPU WITHOUT GPU
llama-modchip runs DeepSeek-V4-Flash 284B on pure 64GB CPU RAM: 44.4 tok/s prefill, 9-14 tok/s generation. 30B MoE models up to 111 tok/s. 256K context, Claude Code resto
★ 1,234 · PythonMULTIMODAL FUTURE IS HERE
Fully open-source framework for training multimodal models — accessible to everyone. Python.
★ 1,050 · PythonIMPLEMENTING LLM ARCHITECTURES FROM SCRATCH
The project contains clean implementations of modern LLM architectures in PyTorch. Includes DeepSeek-R1, DeepSeek-V3, Gemma 3, Kimi K2, and Llama 4. Perfect for studying
★ 856 · 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 · PythonPEGAINFER: Rust + CUDA Infer
Pure Rust LLM engine with CUDA acceleration, OpenAI API compatible, runs Qwen3 and Kimi‑K2 without PyTorch.
★ 742 · RustJANAS: FAST LLM INFERENCE!!
janas runs huge LLM (up to 48 GB) on a 32 GB laptop, outpacing llama.cpp 8‑10×. On Qwen3-Next-80B it gives 37 tok/s w/o draft and 62 tok/s reading GGUF. Supports CPU+GPU
★ 712 · CTENSORSHARP - 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#AUTOMODEL — DISTRIBUTED LLM/VLM TRAINING
Native PyTorch library for distributed LLM/VLM training with out-of-the-box Hugging Face support. ⭐ 576 stars on GitHub.
★ 576 · PythonQWEN3.6-27B ULTIMATE VERSION
Fully uncensored, enhanced version of Qwen3.6-27B with NVFP4 and DFlash speculative decoding.
★ 495 · PythonZINC - LOCAL LLM ON GPU
Zinc is an LLM inference engine in Zig that runs on AMD GPU and Apple Silicon without external dependencies.
★ 395 · ZigLLAMAMPERE: LLM ACCELERATION ON RTX 3090
llama.cpp fork optimized for Ampere GPUs. Delivers 110+ tok/s on Qwen 3.8 at 100K context. Runs on 12 GB VRAM with 200K+ context.
★ 380 · C++HUD-Python RL Evaluation
An OSS environment for RL with ready‑to‑use agent evaluation tools. Run, configure, and get results.
★ 329 · PythonLLM-TPU - RUN AI ON BM1684X
Run generative AI models on Sophgo BM1684X/BM1688 with high speed and low power consumption.
★ 323 · C++JITLLM: HIGH PERFORMANCE LLM ON JVM
JITLLM — Java framework for high‑performance LLM inference and serving on the JVM. Supports GPU acceleration, GGUF and quantized model formats, and integration with DeepS
★ 295 · JavaAESTHETIC HTML/CSS GENERATION FROM PROMPTS
AesCode turns prompts into editable HTML/CSS infographics. Uses image generators as aesthetic guidance and cross-modal rewards with RL (Qwen3) for verifiable code. 225★ o
★ 281 · PythonAI Agent Recovery Controller
Open-source tool for managing execution and recovery of AI agents that use code and external tools. Ensures reliable task execution and automatic rollback on errors.
★ 54 · PythonTraining GPT for $50
The project shows how to train your own GPT-like model on a $50 budget using accessible cloud resources and open-source code.
★ 45 · PythonNew projects on this topic in Telegram
Telegram →