Git Stars Git Stars

#qwen Repositories

143
Total Repositories
1.5M
Total Stars
10,362
Avg Stars/Repo
101
nace-ai/kapitsa

Blazing-fast Apple Silicon inference engine optimized for Qwen & Nemotron. Compatible with the OpenAI and Anthropic APIs. Built by the team at nace.ai

nace-ai
โญ 840 C++ ๐Ÿ‘ค nace-ai Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-10-16
102
llama-farm/llamafarm

Deploy any AI model, agent, database, RAG, and pipeline locally or remotely in minutes

llama-farm
โญ 837 Python ๐Ÿ‘ค llama-farm Organization ๐Ÿ• Updated 2026-06-10 ๐Ÿ“… Created 2025-07-09
103
helixml/helix

โ™พ๏ธ Private Agent Fleet with Spec Coding. Each agent gets their own GPU-accelerated desktop. Run Claude, Codex, Gemini and open models on a full private AI Stack โ™พ๏ธ

helixml
โญ 833 Go ๐Ÿ‘ค helixml Organization ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2023-10-17
104
johnmai-dev/ChatMLX

๐Ÿค–โœจChatMLX is a modern, open-source, high-performance chat application for MacOS based on large language models.

johnmai-dev
โญ 830 Swift ๐Ÿ‘ค johnmai-dev User ๐Ÿ• Updated 2025-03-12 ๐Ÿ“… Created 2024-03-05
105
CHATS-lab/verbalized-sampling

Verbalized Sampling, a training-free prompting strategy to mitigate mode collapse in LLMs by requesting responses with probabilities. Achieves 2-3x diversity improvement while maintaining quality. Model-agnostic framework with CLI/API for creative writing, synthetic data generation, and dialogue simulation.

CHATS-lab
โญ 828 Python ๐Ÿ‘ค CHATS-lab Organization ๐Ÿ• Updated 2026-11-08 ๐Ÿ“… Created 2025-05-20
106
shuxiachai/academic-commercialization-agent

An AI multi-agent tool that turns research papers into cited commercialization and technology-transfer assessments covering TRL, the patent landscape, markets, and risks. Built with CrewAI + FastAPI, with a reproducible benchmark.

shuxiachai
โญ 819 Python ๐Ÿ‘ค shuxiachai User ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-06-25
107
flashrt-project/FlashRT

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

flashrt-project
โญ 817 C++ ๐Ÿ‘ค flashrt-project Organization ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2026-04-28
108
ARahim3/kaggle-tpu-lab

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.

ARahim3
โญ 812 Python ๐Ÿ‘ค ARahim3 User ๐Ÿ• Updated 2026-10-06 ๐Ÿ“… Created 2026-08-31
109
coderonion/awesome-llm-and-aigc

๐Ÿš€๐Ÿš€๐Ÿš€A 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.

coderonion
โญ 810 ๐Ÿ‘ค coderonion User ๐Ÿ• Updated 2025-08-01 ๐Ÿ“… Created 2023-02-15
110
zhanshijinwat/Steel-LLM

Train a 1B LLM with 1T tokens from scratch by personal

zhanshijinwat
โญ 806 Jupyter Notebook ๐Ÿ‘ค zhanshijinwat User ๐Ÿ• Updated 2025-04-27 ๐Ÿ“… Created 2024-03-16
111
MigoXLab/dingo

Dingo: A Comprehensive AI Data, Model and Application Quality Evaluation Tool

MigoXLab
โญ 771 Python ๐Ÿ‘ค MigoXLab Organization ๐Ÿ• Updated 2026-11-19 ๐Ÿ“… Created 2024-12-24
112
BoltzmannEntropy/MimikaStudio

MimikaStudio - A local-first application for macOS (Apple Silicon) + Agentic MCP Support

BoltzmannEntropy
โญ 753 Dart ๐Ÿ‘ค BoltzmannEntropy User ๐Ÿ• Updated 2026-10-27 ๐Ÿ“… Created 2026-01-26
113
pegainfer-project/pegainfer

Pure Rust + CUDA LLM inference engine โ€” no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2

pegainfer-project
โญ 748 Rust ๐Ÿ‘ค pegainfer-project Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-02-17
114
rasonyang/ai-native-callcenter

Self-hosted, API-first AI call center: AI talks, code controls the call. AI agents answer every call; humans can take over without dropping it. Runs on FreeSWITCH with your SIP trunk and a real-time model (OpenAI, Grok, Qwen, Doubao, or any compatible gateway).

rasonyang
โญ 707 Go ๐Ÿ‘ค rasonyang User ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2026-08-11
115
pcliangx/AppGenesisForge

AI Agent Team scaffold for Claude Code โ€” 19 roles collaborate through stage gates, enforced by mandatory skills + blocking hooks + DoD checklists. Spec-driven change folders, SIT-audited code reviews, 4-layer hook defense, multi-LLM (DeepSeek/Doubao/Qwen/MiniMax). Tracks: Web ยท WeChat Mini Program ยท Apple native (macOS/iOS). ไธญๆ–‡/EN README.

pcliangx
โญ 705 Python ๐Ÿ‘ค pcliangx User ๐Ÿ• Updated 2026-07-19 ๐Ÿ“… Created 2026-04-28
116
X-D-Lab/MindChat

๐Ÿ‹MindChat (Mindspeech) โ€“ Psychological Large Model: Chatting about life's journey, facing hardships with a smile

X-D-Lab
โญ 696 Python ๐Ÿ‘ค X-D-Lab Organization ๐Ÿ• Updated 2024-09-13 ๐Ÿ“… Created 2023-07-06
117
zhongkaifu/TensorSharp

A native .NET LLM inference engine and agent runtime for GGUF models. TensorSharp provides a console application, a web-based chatbot interface, an iPhone app, and Ollama/OpenAI-compatible HTTP APIs for programmatic access. It supports Windows, macOS, iOS, and Linux with full GPU capability.

zhongkaifu
โญ 681 C# ๐Ÿ‘ค zhongkaifu User ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2026-04-03
118
Coobiw/MPP-LLaVA

Personal Project: MPP-Qwen14B & MPP-Qwen-Next(Multimodal Pipeline Parallel based on Qwen-LM). Support [video/image/multi-image] {sft/conversations}. Don't let the poverty limit your imagination! Train your own 8B/14B LLaVA-training-like MLLM on RTX3090/4090 24GB.

Coobiw
โญ 678 Jupyter Notebook ๐Ÿ‘ค Coobiw User ๐Ÿ• Updated 2025-03-10 ๐Ÿ“… Created 2023-10-24
119
carloslfu/slotstream

Run a 105 GB AI model on a Mac that can't hold it. Qwen3.8-Flash-Next 4-bit, streamed from SSD on 16โ€“64 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.

carloslfu
โญ 674 Swift ๐Ÿ‘ค carloslfu User ๐Ÿ• Updated 2026-11-17 ๐Ÿ“… Created 2026-08-28
120
leonickson1/Swiftlet

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.

leonickson1
โญ 667 Swift ๐Ÿ‘ค leonickson1 User ๐Ÿ• Updated 2026-11-17 ๐Ÿ“… Created 2026-08-03
121
onejune2018/Awesome-LLM-Eval

Awesome-LLM-Eval: a curated list of tools, datasets/benchmark, demos, leaderboard, papers, docs and models, mainly for Evaluation on LLMs. A curated list of tools, benchmarks/datasets, demos, leaderboards, and large models, primarily focused on the evaluation of foundation large models, aiming to explore the technological boundaries of generative AI.

onejune2018
โญ 661 ๐Ÿ‘ค onejune2018 User ๐Ÿ• Updated 2025-11-24 ๐Ÿ“… Created 2023-04-26
122
shuishuipingan/qoder2api-hub

Qoder multi-account reverse-proxy gateway for international and domestic access; a dual-region, multi-account OpenAI-compatible gateway hub for Qoder โ€” COSY-signed inference, stable device fingerprints to prevent risk controls, OAuth device authorization for login without a client, daily check-ins and Pro benefits, a background scheduler, and a Web monitoring dashboard. Supports Codex / Claude Code and standard OpenAI clients.

shuishuipingan
โญ 656 Python ๐Ÿ‘ค shuishuipingan User ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-09-19
123
Piebald-AI/awesome-gemini-cli

A curated list of awesome tools, extensions, and resources for Gemini CLI.

Piebald-AI
โญ 649 ๐Ÿ‘ค Piebald-AI Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2025-07-30
124
huawei-csl/SINQ

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]

huawei-csl
โญ 638 Python ๐Ÿ‘ค huawei-csl Organization ๐Ÿ• Updated 2026-05-08 ๐Ÿ“… Created 2025-09-26
125
owenliang/qwen-vllm

Tongyi Qianwen VLLM Inference Deployment DEMO

owenliang
โญ 637 Python ๐Ÿ‘ค owenliang User ๐Ÿ• Updated 2024-03-28 ๐Ÿ“… Created 2024-01-21
126
wildminder/ComfyUI-DyPE

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

wildminder
โญ 635 Python ๐Ÿ‘ค wildminder User ๐Ÿ• Updated 2026-10-24 ๐Ÿ“… Created 2025-10-27
127
jianzhnie/LLamaTuner

Easy and Efficient Finetuning LLMs. (Supported LLama, LLama2, LLama3, Qwen, Baichuan, GLM, Falcon) Efficient Quantization Training + Deployment of Large Models.

jianzhnie
โญ 620 Python ๐Ÿ‘ค jianzhnie User ๐Ÿ• Updated 2025-01-24 ๐Ÿ“… Created 2023-05-25
128
eudk/awesome-ai-tools

๐Ÿ”ด VERY LARGE AI TOOL LIST! ๐Ÿ”ด Curated list of AI Tools - Updated 2026

eudk
โญ 614 ๐Ÿ‘ค eudk User ๐Ÿ• Updated 2026-06-07 ๐Ÿ“… Created 2023-12-22
129
wzdnzd/harvester

Intelligent data acquisition framework for GitHub and web sources

wzdnzd
โญ 612 Python ๐Ÿ‘ค wzdnzd User ๐Ÿ• Updated 2026-06-23 ๐Ÿ“… Created 2025-08-11
130
lucienhuangfu/eLLM

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

lucienhuangfu
โญ 602 Rust ๐Ÿ‘ค lucienhuangfu User ๐Ÿ• Updated 2026-11-12 ๐Ÿ“… Created 2025-06-30
131
kapi2800/qwen3-tts-apple-silicon

Run Qwen3-TTS text-to-speech locally on Mac (M1/M2/M3/M4). Voice cloning, voice design, custom voices. 100% offline using MLX.

kapi2800
โญ 593 Python ๐Ÿ‘ค kapi2800 User ๐Ÿ• Updated 2026-05-02 ๐Ÿ“… Created 2026-01-28
132
pdsuwwz/chatgpt-vue3-light-mvp

A secondary development-ready Chat Bot single-turn dialogue Web MVP prototype template, built with mainstream technologies including Vue 3, Vite 8, TypeScript, Naive UI, Pinia (v3), and UnoCSS. ๐Ÿงค Features simple integration of LLM APIs, single-turn AI Q&A mode with independent responses (no context required), SSE typewriter-effect streaming output, and integrated markdown-it with Mermaid/KaTex/LaTex formula highlighting. Supports iFlytek Spark, Zhipu AI, SiliconFlow, and DeepSeek V4/V3/R1 deep reasoning model previews, compatible with <think> tags, and includes distilled skills. ๐Ÿ’ผ Easy to customize and rapidly build Chat-based LLM products (example screenshots included).

pdsuwwz
โญ 586 Vue ๐Ÿ‘ค pdsuwwz User ๐Ÿ• Updated 2026-07-31 ๐Ÿ“… Created 2024-07-25
133
zjhellofss/KuiperLLama

Campus recruitment, fall recruitment, spring recruitment, great internship projects, guiding you to implement from scratch a large model inference framework supporting Llama2/3 and Qwen2.5.

zjhellofss
โญ 581 C++ ๐Ÿ‘ค zjhellofss User ๐Ÿ• Updated 2025-10-28 ๐Ÿ“… Created 2024-04-25
134
TsinghuaC3I/MARTI

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

TsinghuaC3I
โญ 575 Python ๐Ÿ‘ค TsinghuaC3I Organization ๐Ÿ• Updated 2026-08-20 ๐Ÿ“… Created 2025-05-10
135
yassa9/qwen600

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

yassa9
โญ 559 Cuda ๐Ÿ‘ค yassa9 User ๐Ÿ• Updated 2025-09-08 ๐Ÿ“… Created 2025-09-06
136
mco-org/mco

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

mco-org
โญ 558 Python ๐Ÿ‘ค mco-org Organization ๐Ÿ• Updated 2026-11-06 ๐Ÿ“… Created 2026-02-26
137
OmniJev/Flide

๐Ÿ”ฅ๐Ÿ”ฅ The extremely fast inference engine for decision models

OmniJev
โญ 550 Python ๐Ÿ‘ค OmniJev Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-10-24
138
Indras-Mirror/Xolotl

Xolotl: run DeepSeek-V4.1-Flash, all 552B parameters, as a local coding agent on one gaming PC (RTX 4090 + 110 GB RAM): ~33 tok/s agent, ~41 fast, 512K context. Plus Inkling-2-Mini (Thinking Machines, own engine + MTP drafter), GLM-5.3-Flash, Qwen3.8, LFM3-Omni. MoE experts tiered across VRAM, RAM, and NVMe (Xolotl Direct). OpenAI + Anthropic API.

Indras-Mirror
โญ 549 C++ ๐Ÿ‘ค Indras-Mirror User ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-10-06
139
MemTensor/MemT-1.0

Official repository for MemT-1.0

MemTensor
โญ 545 Python ๐Ÿ‘ค MemTensor Organization ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2026-10-19
140
beiwocaishijia/gezhi-sheets

Gezhi AI ยท Gezhi Sheets | Make spreadsheets understand you. A local AI spreadsheet assistant supporting GLM, Kimi, Doubao, DeepSeek, and Qwen.

beiwocaishijia
โญ 537 JavaScript ๐Ÿ‘ค beiwocaishijia User ๐Ÿ• Updated 2026-11-18 ๐Ÿ“… Created 2026-11-09
141
ome-projects/ome

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

ome-projects
โญ 529 Go ๐Ÿ‘ค ome-projects Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2025-05-19
142
modelstudioai/cli

Official Model Studio CLI (Alibaba Cloud Bailian CLI) built for AI Agent frameworks, exposing models, search, multimodal, and workflow capabilities as structured tool calls.

modelstudioai
โญ 526 TypeScript ๐Ÿ‘ค modelstudioai Organization ๐Ÿ• Updated 2026-10-12 ๐Ÿ“… Created 2026-05-28
143
Piebald-AI/gemini-cli-desktop

Web/desktop UI for Gemini CLI/Qwen Code. Manage projects, switch between tools, search across past conversations, and manage MCP servers, all from one multilingual interface, locally or remotely.

Piebald-AI
โญ 522 TypeScript ๐Ÿ‘ค Piebald-AI Organization ๐Ÿ• Updated 2026-11-19 ๐Ÿ“… Created 2025-07-27
144
AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-DFlash

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.

AEON-7
โญ 501 Python ๐Ÿ‘ค AEON-7 User ๐Ÿ• Updated 2026-11-13 ๐Ÿ“… Created 2026-04-25
145
dineshsoudagar/local-llms-on-android

Run local LLMs like Gemma, Qwen, and LLaMA on Android for offline, private, real-time chat and question answering with LiteRT and ONNX Runtime.

dineshsoudagar
โญ 501 Kotlin ๐Ÿ‘ค dineshsoudagar User ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2025-05-04