Self-hosted alternatives to LocalAI
200 self-hosted apps like LocalAI, closest match first.
Top picks
- O

Ollama
LaunchOllama is a tool for running open AI models on your own computer, from the terminal or through apps you build. It runs on macOS, Windows and Linux. When a model is too large for your hardware, cloud models are available too, paid for with u
- T

TurboLLM
LaunchRun open AI models on your own machine — no cloud, no account, fully offline. Any GGUF model on any llama.cpp-compatible engine, auto-tuned to your hardware, with real measured tokens/sec before you download, a fast browser UI, and an OpenA
- T
Textgen
LaunchTextGen is an open-source desktop app for running large language models locally. It has a chat and generation interface, and an OpenAI- and Anthropic-compatible API. The project's own description says it has no telemetry and works fully off
- L
Llmaker
LaunchModels, vector DBs, embeddings, a retrieval agent, and evals: the whole modern LLM stack on your own hardware, from one command. OpenAI-compatible API + web UI per instance, GPU partitioning, no data leaving your machine.
- L

Locally Uncensored
LaunchThe all-in-one local AI studio for your desktop: chat, image and video generation and a coding agent in one free, open source app. Windows and Linux. No Docker, no terminal, no cloud required.
- S
Self-Hosted AI Stack
LaunchDeploy a self-hosted AI stack with Docker Compose: local LLMs, chat, document parsing, embeddings, transcription, text-to-speech and MCP tools. Powered by Ollama, LiteLLM, AnythingLLM and more. Local-first with auto-configured authenticatio
More like LocalAI

Inference Gateway
An open-source, cloud-native, high-performance gateway unifying multiple LLM…
About LocalAI
LocalAI
Run LLMs, speech, image generation
LocalAI is an open-source, MIT-licensed AI engine that runs language models, speech, vision, image and video generation and agents on your own hardware. Its API is compatible with OpenAI, and the site says it also speaks the Anthropic, Ollama and ElevenLabs APIs, so most tools only need a new URL. The engine behind the API can be swapped. One model can run on llama.cpp while another runs on vLLM, SGLang or MLX, and clients see the same endpoint. A small core loads each engine as a separate backend only when a model needs it. The site says LocalAI works on any hardware, including CPU-only machines, and lists support for realtime voice, speech synthesis, object detection, depth estimation and image generation. Models are available with one click from a catalog of more than 1,000. The project is on GitHub, with documentation and a blog.
- Price
- Open source
- Category
- AI
- Website
- localai.io





