#qwen3 Repositories
Discover 37 active open source GitHub repositories tagged with #qwen3, accumulating 217,169 total stars (averaging 5,869 stars per project). Leading this topic is vllm-project/vllm with 97,302 stars.
37 repositories total
๐ฅ MaxKB is an open-source platform for building enterprise-grade agents. A powerful and user-friendly open-source platform for enterprise-grade agents.
Use PEFT or full-parameter training for CPT/SFT/DPO/GRPO on 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM5.3, Gemma4, LLaVA, Phi4, ...) (AAAI 2025).
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!
Jev-like family of decision models built on top of Qwen3.5/3.8 that you can train and run yourself
Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code
Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.
๐A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.๐
A native macOS app that allows users to chat with a local LLM that can respond with information from files, folders and websites on your Mac without installing any other software. Powered by llama.cpp.
Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent, 150k-262k context. vLLM patches, requant pipeline, benchmarks.
ASR/STT subtitle generator. Uses Qwen3-ASR, local LLM, Whisper, TEN-VAD. Noise-robust for JAV.
Chat2API enables zero-cost access to leading AI models by leveraging official web UIs. It supports providers such as DeepSeek, GLM, Kimi, MiniMax, Qwen, and Z.ai, and seamlessly integrates with tools like openlcaw, Cline, and Roo-Code.
Local inference that behaves like a frontier API: Qwen3.8-Flash-Next on AMD Strix Halo plus small NPU models, over the OpenAI and Anthropic APIs on one port.
Zero-GPU CPU inference for 30Bโ284B MoE models (Qwen3.8 176.5B cold-cache certified in 28.26/48.35 GiB Cgroup v2, DeepSeek-V4 284B, Nemotron-30B) + RouteCrack 2.0.
AI-powered tool for efficient abstract and PDF screening in systematic reviews.
๐ Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support
๐ฌ 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.
The official implementation for [NeurIPS2025 Oral] Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free
An Open Foundation Model and Benchmark to Accelerate Generative Recommendation
Frontier-class open models on a free Kaggle TPU v5e-8: GLM-5.3-Flash 320B MoE (~165 tok/s, our own JAX engine) and Qwen3.8-27B bf16 (~130 tok/s), 262k context, prefix caching. Works with Claude Code, Codex, opencode and pi.
๐๐๐A 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.
MimikaStudio - A local-first application for macOS (Apple Silicon) + Agentic MCP Support
Pure Rust + CUDA LLM inference engine โ no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2
37 tok/s from Qwen3-Next-80B (48 GB) on a 32 GB laptop, 24 without drafts vs 2.8 for llama.cpp; reading 62 vs 16 tok/s. Faster than llama.cpp on all 13 models compared in Q4_K_M. LLMs bigger than your RAM, pure C, CPU or GPU.
LLM API Gateway - A brand-new AI model interface management and API aggregation distribution system. It supports converting various LLMs into unified OpenAI-compatible, Claude-compatible, and Gemini-compatible interfaces. Suitable for personal or enterprise-level unified API management and channel distribution (key management and secondary distribution). Supports all mainstream international and domestic models such as Gemini, Claude, Qwen3, Kimi-k2, Doubao, etc. Available as a single executable file or Docker image, one-click deployment, out-of-the-box, fully open-source, and self-controllable! This project is based on New-API and One-API, integrating all features of NewAPI and OneAPI along with numerous third-party plugins. Extremely powerful functionality!
Run a 105 GB AI model on a Mac that can't hold it. Qwen3.8-Flash-Next 4-bit, streamed from SSD on 16โ64 GB Apple Silicon Macs. Fully native Swift, MLX and Metal. Offline, no Python. CLI, Swift library, and Ollama/OpenAI/Anthropic APIs. Works with Claude Code and Codex.
Performed concatenated fine-tuning of the SmolVLM2 visual head and the Qwen3-0.6B model.
A pure Rust-based inference engine for LLMs, VLMs, VLAs, TTS, and OCR, powered by Candle and Rust. An alternative to llama.cpp that's much simpler and cleaner.
Fully uncensored, capability-enhanced abliteration of Qwen3.6-27B. NVFP4 + z-lab DFlash speculative decoding (n=12) on the unified ghcr.io/aeon-7/aeon-vllm-ultimate:latest container, tuned for long-context draft acceptance on DGX Spark. 6 HF variants (BF16/NVFP4/MTP/MTP-XS), docker-compose, and QuickStart.
Frequently Asked Questions
What is the most popular #qwen3 repository on GitHub?
The top ranked open source #qwen3 project on GitHub is vllm-project/vllm with 97,302 stars. A high-throughput and memory-efficient inference and serving engine for LLMs
Which programming languages are most used in #qwen3 repositories?
Among the top ranked #qwen3 projects on GitHub, the most common programming languages are Python, Go, Swift, TypeScript.
How is the #qwen3 repository ranking calculated?
We track 37 active open source repositories tagged with #qwen3 (500+ stars), totaling 217,169 stars with an average of 5,869 stars per repository. Rankings update daily from the GitHub API.