Skip to main content
buildradar
Sign in
Topic · qwen

qwen

Tracked open-source repos tagged qwen, sorted by stars.

107 repos
  • Swiftlet@leonickson1

    Swiftlet is a Swift and Metal runtime that runs large Qwen Mixture-of-Experts models locally on Apple devices by streaming expert weights from storage, enabling 35B and 80B models to run with low RAM, including on iPhone.

    631+48Star change over the last 7 days
  • SINQ@huawei-csl

    Welcome to the official repository of SINQ! A novel, fast and high-quality quantization method designed to make any Large Language Model smaller while preserving accuracy [ICML 2026]

    630+1Star change over the last 7 days
  • ComfyUI-DyPE@wildminder

    ComfyUI DyPE+SEGA, enabling artifact-free 4K+ image generation: Z-Image, Qwen, Flux, Krea2

    623+2Star change over the last 7 days
  • LLamaTuner@jianzhnie

    Easy and Efficient Finetuning LLMs. (Supported LLama, LLama2, LLama3, Qwen, Baichuan, GLM , Falcon) 大模型高效量化训练+部署.

    621+0Star change over the last 7 days
  • harvester@wzdnzd

    Intelligent data acquisition framework for GitHub and web sources

    605+1Star change over the last 7 days
  • 🔴 VERY LARGE AI TOOL LIST! 🔴 Curated list of AI Tools - Updated 2026

    580+2Star change over the last 7 days
  • eLLM@lucienhuangfu

    eLLM: Run Long-Horizon Inference Faster on CPUs Than on GPUs

    577Star change over the last 7 days
  • 💭 一个可二次开发 Chat Bot 单轮对话 Web 端 MVP 原型模板, 基于 Vue 3, Vite8, TypeScript, Naive UI, Pinia(v3), UnoCSS 等主流技术构建, 🧤简单集成大模型 API, 采用单轮 AI 问答对话模式, 每次提问独立响应, 无需上下文, 支持 SSE 打字机效果流式输出, 集成 markdown-it Mermaid/KaTex/LaTex 公式高亮预览, 星火, 智谱, 硅基流动, Deepseek V4/V3/R1 深度思考推理模型预览, 兼容 <think> 标签, 包含蒸馏 skill 💼 易于定制和快速搭建 Chat 类大语言模型产品 (附示例截图)

    575+1Star change over the last 7 days
  • KuiperLLama@zjhellofss

    校招、秋招、春招、实习好项目,带你从零动手实现支持LLama2/3和Qwen2.5的大模型推理框架。

    573+0Star change over the last 7 days
  • Run Qwen3-TTS text-to-speech locally on Mac (M1/M2/M3/M4). Voice cloning, voice design, custom voices. 100% offline using MLX.

    561+2Star change over the last 7 days
  • qwen600@yassa9

    Static suckless single batch CUDA-only qwen3-0.6B mini inference engine

    560+0Star change over the last 7 days
  • FlashRT@flashrt-project

    FlashRT is a high-performance realtime inference engine for small-batch, latency-sensitive AI workloads. The flagship integration is production VLA control for Pi0, Pi0.5, GROOT N1.6, and Pi0-FAST. Also support llm e.g, qwen3.6-27B

    555+12Star change over the last 7 days
  • MARTI@TsinghuaC3I

    [ICLR 2026] A Framework for LLM-based Multi-Agent Reinforced Training and Inference

    555+1Star change over the last 7 days
  • BigMoeOnEdge@Helldez

    Run MoE models bigger than your RAM. Frontier-size MoE on a 12 GB phone, CPU only, lossless, on stock llama.cpp

    550+18Star change over the last 7 days
  • mco@mco-org

    CLI-first orchestration for AI coding agents: run selected agents and models in parallel, compare raw answers, and coordinate review or implementation workflows.

    515+5Star change over the last 7 days
  • ome@ome-projects

    Open Model Engine (OME) — Kubernetes operator for LLM serving, GPU scheduling, and model lifecycle management. Works with SGLang, vLLM, TensorRT-LLM, and Triton

    508+3Star change over the last 7 days
  • A curated list of awesome tools, extensions, and resources for Gemini CLI.

    504Star change over the last 7 days
← Back to topics