LLMs-local
A curated, categorized list of platforms, engines, user interfaces, models, tools, and tutorials for running large language models locally.
LLMs-local is a curated list of platforms, tools, and resources for running large language models on a user's own hardware. It is organized into sections covering inference platforms such as LM Studio, Jan, and LocalAI; inference engines such as Ollama, llama.cpp, vLLM, and exo; user interfaces such as Open WebUI, Lobe Chat, and Text Generation WebUI; large language models, including explorers, benchmarks, leaderboards, model providers, and models grouped by purpose; tools for agent frameworks, MCP, retrieval-augmented generation, coding agents, computer use, browser automation, memory management, testing and evaluation, research, and training and fine-tuning; hardware; tutorials on models, prompt and context engineering, inference, agents and RAG; and communities.
Each entry is a short, linked description rather than an in-depth writeup.