Self-hosted alternatives to Ollama
200 self-hosted apps like Ollama, closest match first.
Top picks
- 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
Free
- L

LocalAI
LaunchLocalAI 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, Olla
Free
- 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.
Free
- O

Open WebUI
LaunchOpen WebUI is a self-hosted AI platform for running and chatting with models on your own machine or server. It connects to local models and to cloud providers, including Ollama, OpenAI, Anthropic and any compatible API. You can extend it wi
Free
- O
OpenGateLLM
LaunchOpenGateLLM is an open-source API gateway for generative AI. It is built for organizations that want full control over their data and infrastructure, and it is optimized for self-hosted models. The gateway centralizes, secures and governs a
Free
- O
overtchat
LaunchA polished, privacy-first Open WebUI alternative for local and hosted models, with multi-user accounts, realtime local voice, files, search, memory, and desktop and mobile apps.
Free
More like Ollama

Inference Gateway
An open-source, cloud-native, high-performance gateway unifying multiple LLM…
Self-Hosted AI Stack
Deploy a self-hosted AI stack with Docker Compose: local LLMs, chat, document…
OmniKey-AI-Unified-Key-Manager
A self-hosted LLM proxy and failover gateway supporting OpenAI & Gemini…
About Ollama
Ollama
Load and run large LLMs locally to use in your terminal or build your apps
Ollama 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 usage credits. The site says prompts sent to its models are never stored or trained on. Its library holds many popular open models, and the site reports more than a billion model downloads. The free plan lets you run models locally, with starter credits for cloud models and access to starter models. Paid Pro, Max and Team plans add monthly usage credits, larger models and concurrent requests. The Team plan adds unlimited users, shared credits across a team, centralized billing and administration. Ollama also has a GitHub project, a Discord community, documentation and a blog.
- Price
- Freemium
- Category
- AI
- Website
- ollama.com



