#qwen Repositories
145 repositories total
Blazing-fast Apple Silicon inference engine optimized for Qwen & Nemotron. Compatible with the OpenAI and Anthropic APIs. Built by the team at nace.ai
Deploy any AI model, agent, database, RAG, and pipeline locally or remotely in minutes
โพ๏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 โพ๏ธ
๐คโจChatMLX is a modern, open-source, high-performance chat application for MacOS based on large language models.
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.
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.
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
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
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).
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.
๐MindChat (Mindspeech) โ Psychological Large Model: Chatting about life's journey, facing hardships with a smile
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.
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.
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.
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.
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.
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.
A curated list of awesome tools, extensions, and resources for Gemini CLI.
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]
ComfyUI DyPE+SEGA, enabling artifact-free 4K+ image generation: Z-Image, Qwen, Flux, Krea2
Easy and Efficient Finetuning LLMs. (Supported LLama, LLama2, LLama3, Qwen, Baichuan, GLM, Falcon) Efficient Quantization Training + Deployment of Large Models.
๐ด VERY LARGE AI TOOL LIST! ๐ด Curated list of AI Tools - Updated 2026
Run Qwen3-TTS text-to-speech locally on Mac (M1/M2/M3/M4). Voice cloning, voice design, custom voices. 100% offline using MLX.
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. ๐งค 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. ๐ผ Easy to customize and rapidly build Chat-based LLM products (example screenshots included).
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.
[ICLR 2026] A Framework for LLM-based Multi-Agent Reinforced Training and Inference
CLI-first orchestration for AI coding agents: run selected agents and models in parallel, compare raw answers, and coordinate review or implementation workflows.
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.
Gezhi AI ยท Gezhi Sheets | Make spreadsheets understand you. A local AI spreadsheet assistant supporting GLM, Kimi, Doubao, DeepSeek, and Qwen.
Open Model Engine (OME) โ Kubernetes operator for LLM serving, GPU scheduling, and model lifecycle management. Works with SGLang, vLLM, TensorRT-LLM, and Triton
Official Model Studio CLI (Alibaba Cloud Bailian CLI) built for AI Agent frameworks, exposing models, search, multimodal, and workflow capabilities as structured tool calls.
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.
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.
Run local LLMs like Gemma, Qwen, and LLaMA on Android for offline, private, real-time chat and question answering with LiteRT and ONNX Runtime.