# Ollama Ollama is a local runtime for large language models (LLMs) that provides an application programming interface (API) and command-line interface (CLI) for pulling, managing, and querying models on your own hardware, with. It is open source and self-hosted, installable on Docker Hub, Proxmox, Kubernetes (Helm), ZimaOS, TrueNAS, Umbrel and Unraid. Canonical page: https://ourlocalhost.com/app/38/ollama ## Description Ollama is a local runtime for large language models (LLMs) that provides an application programming interface (API) and command-line interface (CLI) for pulling, managing, and querying models on your own hardware, with graphics processing unit (GPU) acceleration for Nvidia and AMD systems, so homelabbers can run private, offline-capable model serving without cloud providers. ## Platform availability Available on 6 of 9 platforms: Unraid, TrueNAS, Umbrel, ZimaOS, Proxmox, Helm. ## Health score 27/100 (Low), based on 3 of 4 factors. - Maintained: 0 (GitHub repository no longer exists) - Easy to install: 85 (6 install platforms, install notes, Docker image) - Light to run: 20 (8 GB minimum RAM, runs on ARM) ## Links - Documentation: https://docs.ollama.com/ - Docker Hub: https://hub.docker.com/r/ollama/ollama/ - Official website: https://ollama.ai/ - Proxmox: https://community-scripts.github.io/ProxmoxVE/scripts?id=ollama - Kubernetes (Helm): https://artifacthub.io/packages/helm/ollama-helm/ollama - ZimaOS: https://github.com/IceWhaleTech/CasaOS-AppStore/tree/main/Apps/Ollama - TrueNAS: https://apps.truenas.com/catalog/ollama/ - Umbrel: https://apps.umbrel.com/app/ollama - Unraid: https://ca.unraid.net/apps/ollama-0kwfjrc14pdjrg?q=ollama - GitHub: https://github.com/ollama/ollama ## Common questions ### Do I need to sign in to use Ollama locally? Sign in only if you need cloud models. Skipping the cloud sign-in will make cloud model requests fail. ### Can Ollama accept multiple simultaneous connections? Yes, it can be run as an HTTP server so several connections can be made at the same time. It also fits well with Open WebUI. ### How do I check which `ollama launch` integrations my version supports? Run `ollama launch --help` for the list on your version. The available coding integrations shift from release to release. ### What common Ollama self-hosting problems should I investigate? Check for GPU not detected, OOM model loads, slow tokens, missing models, and Ollama service failures. ## Alternatives - Agora: Agora is a digital shopfront that allows you to sell files directly to others. - Alpaca - Ollama Client: Alpaca is an Ollama client where you can manage and chat with multiple models, Alpaca provides an easy and begginer friendly way of interac… - AnythingLLM: AnythingLLM is a local, all-in-one AI app for self-hosters that works with any large language model, providing document chat, retrieval-aug… - Ensu: Private offline on-device local LLM app by Ente, open source code, no accounts or tracking, and works cross-platform on mobile and desktop… - Google AI Edge Gallery: A gallery that showcases on-device ML/GenAI use cases and allows people to try and use models locally. - Jan.ai: Open-source offline AI chat software supporting local LLMs, cloud model connections, custom assistant creation, OpenAI-compatible API, and… - LM Studio: LM Studio is an application for running and experimenting with local large language models (LLMs) such as gpt-oss, Llama, Gemma, Qwen, and… - LocalAI: LocalAI is a free, open-source, self-hosted AI engine that provides a drop-in, OpenAI-compatible API for running local models. - PocketPal: An app that brings language models directly to your phone. - Private GPT: Ask questions to your documents without an internet connection, using the power of LLMs. - lemonade-server: Lemonade helps users discover and run local AI apps by serving optimized LLMs right from their own GPUs and NPUs. - llama.cpp: Llama.cpp is a pure C/C++ inference engine for large language models, including Meta's LLaMA. --- Source: Our Local Host (https://ourlocalhost.com/app/38/ollama), the self-hosted and open-source app directory.