Ollama
 Ollama logo | |
| Developer(s) | Ollama, Inc. |
|---|---|
| Initial release | 2023 |
| Written in | Go |
| Engine | |
| Operating system | macOS, Linux, Windows |
| Type | Large language model runtime |
| Website | https://ollama.com |
Search Ollama on Amazon.
Ollama is an open source software framework for managing and running large language models (LLM) locally or in the cloud. It enables quick deployment of LLMs and offers a command-line interface (CLI) for downloading, installing, using and removing models. By providing a uniform interface to the models it supports, it enables users to use models whose details they are not familiar with allowing them to run LLMs locally on computer hardware.
Architecture
At the core of Ollama is a local web server and a client server architecture that provides a JSON REST API for managing models and interacting with them. The ollama program starts and manages that server and uses the REST API to provide a CLI for managing models and interacting with them.[1][2]
On its own, Ollama does not have a graphical user interface. For this purpose,Open WebUI can be used as an interface.[1]
Website
Ollama has its own website,[3] which allows users to download large language models through the terminal, such as Kimi, DeepSeek, and Llama.[4]
Implementation
Ollama is primarily written in Go. The software integrates inference components derived from llama.cpp, which are implemented largely in C and C++ for efficient execution of large language models on local hardware.[5] It is commonly run on a computer terminal.[6]
Ollama supports Apple's MLX framework in a preview with the model Qwen3.5.[7]
References
- ↑ 1.0 1.1 Wolski, David. "KI lokal auf dem PC nutzen: So geht´s mit Ollama ganz einfach". PC-Welt. Retrieved 24 October 2025.
- ↑ S. Marcondes, Francisco; Gala, Adelino; Magalhaes, Reneta; Perez de Britto, Fernando; Duraes, Dalila; ovais, Paulo (2025). Natural Language Analytics with Generative Large-Language Models (1 ed.). Springer. p. 23-35. ISBN 9783031766305. Retrieved 1 April 2026. Search this book on
- ↑ "Ollama Official Website". Ollama Official Website. Retrieved 6 Aug 2025.
- ↑ https://ollama.com/library
- ↑ ollama/ollama, Ollama, 2026-03-13, retrieved 2026-03-13
- ↑ https://arxiv.org/pdf/2603.23996
- ↑ Axon, Samuel (April 1, 2026). "Running local models on Macs gets faster with Ollama's MLX support". Ars Technica. Retrieved April 4, 2026.
This article "Ollama" is from Wikipedia. The list of its authors can be seen in its historical and/or the page Edithistory:Ollama. Articles copied from Draft Namespace on Wikipedia could be seen on the Draft Namespace of Wikipedia and not main one.
