Best Open Source LLMs

Langflow is a powerful tool for building and deploying AI-powered agents and workflows.

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, moss等。

《深入理解 AI Agent：设计原理与工程实践》（李博杰 著）开源主仓库：全书正文、编译版 PDF 与按章配套代码

Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

[EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation

A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.

🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform.

Build and run agents you can see, understand and trust.

A one stop repository for generative AI research updates, interview resources, notebooks and much more!

Official code repo for the O'Reilly Book - "Hands-On Large Language Models"

Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.

Distribute and run LLMs with a single file.

🚀 A curated collection of AI engineering resources, roadmaps, tools, and projects covering LLMs, RAG, AI Agents, MCP, fine-tuning, evaluations, and production AI systems.

The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.

FinGPT: Open-Source Financial Large Language Models! Revolutionize 🔥 We release the trained model on HuggingFace.

Code for Machine Learning for Trading, 3rd edition - from data sourcing to live execution.

Machine Learning Engineering Open Book

中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)

Ongoing research training transformer models at scale

:sparkles::sparkles:Latest Advances on Multimodal Large Language Models

🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org

Sample code and notebooks for Generative AI on Google Cloud, with Gemini Enterprise Agent Platform

Automated Penetration Testing Agentic Framework Powered by Large Language Models

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows

A curated list of modern Generative Artificial Intelligence projects and services

Pocket Flow: Codebase to Tutorial

Hierarchical Reasoning Model Official Release

An open-source, tool-augmented conversational language model from Fudan University

A straightforward method for training your LLM, from downloading data to generating text.

Pocket Flow: 100-line LLM framework. Let Agents build Agents!

A curated list of 120+ LLM libraries category wise.

A curated list of practical guide resources of LLMs (LLMs Tree, Examples, Papers)

An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)

High-speed Large Language Model Serving for Local Deployment

Anomaly detection related books, papers, videos, and toolboxes. Last update late 2025 for LLM and VLM works!

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.

NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness.

大模型（LLM）全栈学习路线与中文教程🔥：覆盖 Prompt Engineering、RAG、AI Agent、MCP、微调、模型部署、Transformer、AI 编程与大厂面试，从入门到生产实践。

Your iPhone helps your Mac run a 27B model: faster prompt reading and more context over a USB-C cable

The fastest way to run Qwen3.8-Flash-Next on Strix Halo (gfx1151)

Run full Kimi K3 on a single device. And an OpenAI-compatible API server for local chat and coding agents.

Project Maya - run GLM-5.3-Flash (321B MoE) privately on your own GPU(s), from one card to 16, NVIDIA or AMD, Linux or Windows. Engine, server, dashboard, OpenAI- and Anthropic-compatible API, quant tools.

Halo is an open-source framework built by White Circle for training large language and multimodal models

A clinical decision-evidence benchmark: pull the one fact an answer rests on, and see whether the assistant's action moves with the evidence. Built on HealthBench.

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.

Peer-to-peer LLM inference in the browser: pool your devices to run big open models, for chat and coding agents.

AI Engineering Course - A free and complete AI Engineering Course to learn AI Engineering step by step - from Machine Learning, Neural Networks, and Transformers to LLMs, Fine-Tuning, RAG, AI Agents, LLM Inference, Evaluation, AI Safety, and AI System Design.

本地优先的全栈 AI 创作工作站：AI对话 · AI漫画 · 漫剧创作 · 写作台 · 知识学习五大模块；vLLM / llama.cpp / Transformers 多引擎本地推理，显存智能调度、舱壁隔离自愈、仅供学习使用，欢迎交流指正。（最新进度（除插件系统）受到协议限制，暂时无法提交到仓库）

Run a 105 GB AI model on a Mac that can't hold it. Slotstream streams Qwen3.8-Flash-Next (125B mixture of experts) from your SSD and caches the busiest experts in memory, so it runs on Macs with 16 to 64 GB. One native Swift binary on MLX and Metal, no Python, offline. Works with Claude Code, Codex and Ollama or OpenAI clients.

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.

Local Qwen 3.8 27B uncensored Q4_K_M + harvested SYSTEM pack. Official 3.8 weights, not a 3.6 retitle.

TLive-Omni: An Omni-Modal Understanding Model for E-Commerce Live Streaming

Learn LLM Inference Engineering step by step - from KV cache, PagedAttention, and continuous batching to vLLM, SGLang, and GPUs.

Your car as a chat-room agent: Raspberry Pi 5 + dashcam + local AI. CodeWatch's sibling for the garage.

Open desktop AI agent for Windows, macOS and Linux, written from scratch: its own agent engine, its own browser tooling and its own drawing engine that shows what it explains.