# Best local LLM tools to self-host > To run an LLM locally, the core of a private AI stack is Ollama for running models, Open-WebUI (source-available) for chatting with them and RAGFlow for questions over your own files, all running on your own servers so your prompts and documents can stay on your infrastructure. Each pick was chosen by hand for its job and is shown with GitHub data from October 2026. ## Key facts | Fact | Value | |---|---| | Question | What are the best tools to run an LLM locally? | | Picks | 12 | | Top pick | Ollama (182,289 stars) | | Data as of | Oct 7, 2026 | | Canonical URL | https://appsgit.com/best/local-llm | A local LLM setup has two parts: a model runner that downloads open-weight models and serves them on your own CPU or GPU, and a chat interface on top. Both run on your machine or server, so prompts and documents do not go to a cloud AI provider unless you connect one. ## Model runners Download open-weight models and serve them locally, usually through an OpenAI-compatible API. - [Ollama](https://appsgit.com/apps/ollama) (182,289 stars, MIT, Go, Docker, AI features): Ollama has 182,289 GitHub stars, uses the MIT license, ships a Docker image and had 1,083 commits in the last year; it replaces ChatGPT. - [LocalAI](https://appsgit.com/apps/localai) (49,405 stars, MIT, Go, Docker, AI features): LocalAI has 49,405 GitHub stars, uses the MIT license, ships a Docker image and had 3,438 commits in the last year; it replaces ChatGPT. - [Text Generation WebUI](https://appsgit.com/apps/text-generation-webui) (47,726 stars, AGPL-3.0, Python, Docker, AI features): Text Generation WebUI has 47,726 GitHub stars, uses the AGPL-3.0 license, ships a Docker image and had 744 commits in the last year. - [LLM Harbor](https://appsgit.com/apps/llm-harbor) (3,237 stars, Apache-2.0, Python, Docker, AI features): LLM Harbor has 3,237 GitHub stars, uses the Apache-2.0 license, ships a Docker image and had 1,288 commits in the last year. - [LLMKube](https://appsgit.com/apps/llmkube) (231 stars, Apache-2.0, Go, Docker, AI features): LLMKube has 231 GitHub stars, uses the Apache-2.0 license, ships a Docker image and had 1,039 commits in the last year. ## Chat interfaces Web chat front ends that connect to a local runner (and, if you choose, to cloud APIs). - [Open-WebUI](https://appsgit.com/apps/open-webui) (154,037 stars, Open WebUI License, source-available, Python, Docker, AI features): Open-WebUI has 154,037 GitHub stars, is source-available under the Open WebUI License (BSD-3-Clause plus branding clause) (not an open-source license), ships a Docker image and had 4,746 commits in the last year; it replaces ChatGPT and Lovable. - [LibreChat](https://appsgit.com/apps/librechat) (45,318 stars, MIT, TypeScript, Docker, AI features): LibreChat has 45,318 GitHub stars, uses the MIT license, ships a Docker image and had 2,074 commits in the last year; it replaces ChatGPT and Lovable. - [LobeHub](https://appsgit.com/apps/lobehub) (83,008 stars, LobeHub Community License, source-available, TypeScript, Docker, AI features): LobeHub has 83,008 GitHub stars, is source-available under the LobeHub Community License (not an open-source license), ships a Docker image and had 7,488 commits in the last year; it replaces ChatGPT and Lovable. - [AnythingLLM](https://appsgit.com/apps/anythingllm) (66,738 stars, MIT, JavaScript, Docker, AI features): AnythingLLM has 66,738 GitHub stars, uses the MIT license, ships a Docker image and had 887 commits in the last year; it replaces ChatGPT. - [Onyx Community Edition](https://appsgit.com/apps/onyx-community-edition) (32,332 stars, MIT, Python, Docker, AI features): Onyx Community Edition has 32,332 GitHub stars, uses the MIT license, ships a Docker image and had 5,771 commits in the last year. ## Use them with your documents - [RAGFlow](https://appsgit.com/apps/ragflow) (91,708 stars, Apache-2.0, Go, Docker, AI features): RAGFlow has 91,708 GitHub stars, uses the Apache-2.0 license, ships a Docker image and had 5,821 commits in the last year. - [Khoj](https://appsgit.com/apps/khoj) (37,565 stars, AGPL-3.0, Python, Docker, AI features): Khoj has 37,565 GitHub stars, uses the AGPL-3.0 license, ships a Docker image and had 120 commits in the last year; it replaces ChatGPT. ## How this list was made - Apps were picked by hand from the appsgit catalog for each job, then checked against the snapshot: unknown or archived projects and projects with no commit in two years are dropped automatically. - Inside each section the curated order is kept, most broadly useful first; an app appears only once on the page. - Stars, license, Docker and activity facts come from the GitHub API as of October 2026. - Source-available apps are labelled; they are not open source, so read their licenses before commercial use. ## FAQ ### What hardware do I need to run AI models myself? Small open models run on a modern CPU with 16 GB of RAM, but a GPU with enough video memory for the model you pick makes answers much faster. Start with a small model in Ollama, measure the speed on your own hardware, then size up. ### What is the easiest way to run an LLM locally? Install Ollama, pull a small model and talk to it from the command line, then add a chat interface such as Open WebUI or LibreChat that connects to Ollama's local API. All of them ship Docker images. ### Is Ollama free? Yes. Ollama is open-source software released under the MIT license, so you can self-host it at no cost. You only pay for the server it runs on, and some projects also offer an optional paid cloud plan. ### Can I run this stack with Docker? All 12 apps here publish Docker images, including Ollama, LocalAI and Text Generation WebUI, so most of the stack can run side by side with Docker Compose on one server. Size the server for the heaviest app and add off-site backups. ## Related questions - [What are the best MCP servers for databases?](https://appsgit.com/best/mcp-servers-for-databases) - [What are the best MCP servers for developer tools?](https://appsgit.com/best/mcp-servers-for-developer-tools) - [What are the best MCP servers for web browsing and scraping?](https://appsgit.com/best/mcp-servers-for-web-browsing-scraping) - [What are the best MCP servers for productivity?](https://appsgit.com/best/mcp-servers-for-productivity) - [What are the best MCP servers for cloud and DevOps?](https://appsgit.com/best/mcp-servers-for-cloud-devops) - [What are the best MCP servers for data and analytics?](https://appsgit.com/best/mcp-servers-for-data-analytics) - [What are the best MCP servers for communication?](https://appsgit.com/best/mcp-servers-for-communication) - [What are the best MCP servers for finance?](https://appsgit.com/best/mcp-servers-for-finance) ## See also - [All AI & LLM tools apps](https://appsgit.com/categories/ai-tools) - [Open-source alternatives to ChatGPT](https://appsgit.com/alternatives/chatgpt) - [Open-source alternatives to Lovable](https://appsgit.com/alternatives/lovable) - [Ollama vs LocalAI](https://appsgit.com/compare/ollama-vs-localai) - [Open WebUI vs LibreChat](https://appsgit.com/compare/open-webui-vs-librechat) - [How to self-host Ollama with Docker Compose](https://appsgit.com/guides/ollama) - [How to self-host Open WebUI with Docker Compose](https://appsgit.com/guides/open-webui) --- Canonical page: https://appsgit.com/best/local-llm Source: appsgit (https://appsgit.com), the app store for github. Data from the GitHub API, refreshed nightly. Machine access: JSON API https://appsgit.com/api/v1/apps (OpenAPI: https://appsgit.com/openapi.json), MCP server https://mcp.appsgit.com/mcp, full index https://appsgit.com/llms-full.txt.