#qwen Repositories
145 repositories total
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.
The fastest way to run Qwen 3.8 Flash Next, Qwen 3.8 27B and Ternary Bonsai 2 27B on a Mac: 125 tok/s in OpenCode on an M5 Max, and a 27B model on 16 GB Macs. Native MTP speculative decoding on Apple Silicon, exact at any temperature. OpenAI and Anthropic compatible local server.
Curated AI short drama and manju Skill (skill pack): screenwriting, adaptations, storyboards, and video prompts for Seedance / Kling / MiniMax. Compatible with agents such as Qwen, Doubao, Lobster OpenClaw, WorkBuddy, Claude Code, and Codex | Curated agent skills for AI short dramas, micro dramas / microdramas, vertical dramas, and manju (AI comic dramas): screenwriting, storyboards, and Seedance / Kling / MiniMax video prompts
Brings MCP to ChatGPT, DeepSeek, Perplexity, Grok, Gemini, Google AI Studio, OpenRouter, DeepSeek, T3 Chat and more...
Apple MLX native implementations of state-of-the-art generative image & video models
Openai style api for open large language models, using LLMs just as chatgpt! Support for LLaMA, LLaMA-2, BLOOM, Falcon, Baichuan, Qwen, Xverse, SqlCoder, CodeLLaMA, ChatGLM, ChatGLM2, ChatGLM3 etc. Unified backend API for open large language models
Aix-DB, based on the LangChain/LangGraph framework and combined with the MCP Skills multi-agent collaboration architecture, accomplishes end-to-end conversion from natural language to data insights.
Steering-first neuron explorer for Qwen3.5-4B: push every MLP neuron, keep every rollout, browse the results
Local AI app and inference engine for agents. Run open-weight LLMs locally โ private, 100% offline on your computer. Join our Discord: https://discord.com/invite/8wGSsvmg4V
๐ค Create agentic apps in a second with your prompts. Everything you need to create an LLM Agent โ tools, prompts, frameworks, and models โ all in one place.
A curated list of awesome LLM and AI Agent Skills, resources and tools for customising AI Agent workflows - that works with Claude Code, Codex, Gemini CLI and your custom AI Agents
Cloud native, ultra-high performance AI&API gateway, LLM API management, distribution system, open platform, supporting all AI APIs. Not limited to mainstream models such as OpenAI, Azure, Anthropic Claude, Google Gemini, DeepSeek, ByteDance Doubao, ChatGLM, Baidu Wenxin Yiyan, iFlytek Spark, Alibaba Tongyi Qianwen, 360 Zhinao, Tencent Hunyuan, unified API requests and responses, API application and approval, call statistics, load balancing, multi-model disaster recovery. One-click deployment, ready to use.
Model compression toolkit engineered for enhanced usability, comprehensiveness, and efficiency.
Creating Large Language Models That Understand Social Intelligence | Covers Prompt Engineering, RAG, Agent, LLM Fine-tuning Tutorials
๐๐๐ A collection of some awesome public YOLO object detection series projects and the related object detection datasets.
ใICML 2025 Spotlightใ Official Repo for Paper โโHealthGPT : A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptationโโ
A high-performance inference engine for LLM, VLM, and DiT models, optimized for diverse AI accelerators. It is hosted by the OpenAtom Foundation.
Get up and running with GLM-5.3-flash, DeepSeek, Gemma and other open source frontier models.
PALLAIDIUM โ a generative AI movie studio, seamlessly integrated into the Blender Video Editor (VSE), enabling end-to-end production from script to screen and back.
A novel Multimodal Large Language Model (MLLM) architecture, designed to structurally align visual and textual embeddings.
Parallax is a distributed model serving framework that lets you build your own AI cluster anywhere
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.
Research of DeepSeek Engram Architecture based on Qwen-3 and Stable Diffusion series.
Run large AI models on your own PC: Qwen3.8-Flash-Next on Strata's engine, and GLM 5.3 Flash, DeepSeek V4 Flash, LFM2.5, Qwen3.6, Ornith 1.5, Gemma 4, Tiel Coder, and MiniCPM-V on a second engine built for PolyStrata. One-click installation for Windows and Linux, with an OpenAI/Anthropic API on localhost.
GraphGen: Enhancing Supervised Fine-Tuning for LLMs with Knowledge-Driven Synthetic Data Generation
Bringing together outstanding artificial intelligence (AI) open source projects from around the world.
Your iPhone helps your Mac run a 27B model: faster prompt reading and more context over a USB-C cable
A desktop MCP client designed as a tool unitary utility integration, accelerating AI adoption through the Model Context Protocol (MCP) and enabling cross-vendor LLM API orchestration.
Chat with AI large language models running natively in your browser. Enjoy private, server-free, seamless AI conversations.
Full-stack algorithm tutorial from NLP to LLM, online reading address: https://datawhalechina.github.io/base-llm/
MAC (Multi-Agent CAD): A decoupled multi-agent framework for text-to-CAD generation via constrained test-time compute
74 free LLM API providers & 450+ free models (limits, no-card options) + Free-LLM Router: all of them behind one OpenAI/Anthropic-compatible endpoint with instant failover. Run Claude Code, Codex, Cursor, Aider on free models. Gemini, Groq, Mistral, DeepSeek, Qwen & more. Synced daily.
Run MoE models bigger than your RAM. Frontier-size MoE on a phone, laptop, or edge device. Lossless, on stock llama.cpp. An adaptive streaming optimizer. Any hardware, any OS, any model, any quantization, behind a local OpenAI-compatible server.
A Transparent Generalist Model towards Holistic Medical Vision-Language Understanding
The "FuFan Large Model Technology Community" is a tailored, full-process guide for large model learners of all levels, covering skills including environment setup, local deployment, efficient fine-tuning, and development practice based on various large models!
A powerful model compression framework for LLMs and LVLMs, adapted for NVIDIA GPUs and Huawei Ascend NPUs.
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.
An LLM-powered repository agent designed to assist developers and teams in generating documentation and understanding repositories quickly.
llama.cpp on a jailbroken PS5: run any GGUF model natively on the console, starting with Qwen 3.8
A computer, compiled into the weights of a language model. An exact CPU inside Qwen3.5-4B, with Gated DeltaNet state as RAM.