Ollama
| Ollama | |
|---|---|
| Developers | Ollama Inc. and contributors |
| Initial release | July 7, 2023; 2 years ago (2023年07月07日) |
| Stable release | 0.22.1
/ April 28, 2026; 42 days ago (2026年04月28日) |
| Written in | Go |
| Operating system | macOS, Linux, Windows |
| Type | Large language model runtime |
| License | MIT License |
| Website | ollama |
| Repository | github |
Ollama is an open-source software platform for running and managing large language models on local computers and through hosted cloud models. It provides a command-line interface, a native GUI, a local REST API, model-management tools, and integrations for using open-weight models with coding assistants and other applications.[1] [2] [3]
History
[edit ]Ollama was first released in 2023.[4] The project became associated with the growth of local large language model software, allowing users to download and run models such as Llama, Gemma, Mistral, Qwen, gpt-oss and DeepSeek models from a local machine.[1]
In 2025 and 2026, Ollama added additional application and cloud features, including hosted cloud models, web search support, tool and coding-agent integrations, and support for using Ollama with applications such as Claude Code, Codex, OpenCode, Copilot CLI,[5] and OpenClaw.[2] [6] In March 2026, Ollama announced preview support for Apple's MLX framework on Apple silicon.[7]
Features
[edit ]
Ollama includes tools for downloading, running, importing, and managing large language models. Users can run models from the command line, interact with them through a local HTTP API, or use client libraries for programming languages such as Python and JavaScript.[1]
The project provides a REST API for chat and model-management functions, with the default local service commonly exposed on port 11434.[8] Ollama also distributes an official Docker image and provides model libraries and documentation for running supported models.[1]
Ollama uses the llama.cpp backend for local model inference.[9] It supports a model-library format that allows users to pull, run, and manage model variants by name.[10]
Meanwhile, the project's downloadable software is being explored as a back-end platform for low-code/no-code self-hosting of LLMs, potentially allowing natural language processing use cases to become more accessible to nontechnical end users. [11] [12]
Ollama also has experimental support for image generation, using models such as Flux, on macOS, with Windows and Linux support expected in the future.[13]
Security
[edit ]Because Ollama is commonly used to run local or self-hosted AI models, security researchers have examined risks from misconfigured public deployments. In January 2026, The Hacker News reported on research by SentinelOne and Censys that found many Ollama servers were exposed to the public internet, mainly by binding to the "any" port 0.0.0.0 which on an inadequately-secured system would allow access from other local or remote devices despite the fact that Ollama is intended to run locally by default.[14]
See also
[edit ]- Large language model
- Generative artificial intelligence
- llama.cpp
- vLLM
- SGLang
- List of open-source artificial intelligence software
References
[edit ]- ^ a b c d "ollama/ollama". GitHub . Retrieved April 29, 2026.
- ^ a b "Ollama". Ollama. Retrieved April 29, 2026.
- ^ SitePoint Team (April 22, 2026). "10GB VRAM Local LLM: The Complete Setup Guide (2026)". SitePoint. Retrieved April 29, 2026.
- ^ "Versions: github.com/ollama/ollama". deps.dev. Retrieved April 29, 2026.
- ^ "About GitHub Copilot CLI". GitHub Docs. GitHub. Retrieved April 29, 2026.
- ^ "Blog". Ollama. Retrieved April 29, 2026.
- ^ Medina, David (March 31, 2026). "Ollama Taps Apple's MLX Framework to Make Local AI Faster". The New Stack. Retrieved April 29, 2026.
- ^ "API reference". Ollama Docs. Retrieved April 29, 2026.
- ^ "Forensic Implications of Localized AI: Artifact Analysis of Ollama, LM Studio, and llama.cpp". arxiv.org. Retrieved May 22, 2026.
- ^ "Library". Ollama. Retrieved April 29, 2026.
- ^ Sempio, Julius (March 31, 2026). "Low-Code Self-Hosting of RAG-Enabled Language Models Using Ollama and Open WebUI". IEEE Xplore. doi:10.1109/ICAIIC68212.2026.11454259 . Retrieved May 20, 2026.
- ^ "Low-Code vs. No-Code: What's the difference?". IBM Cloud Education. Retrieved June 4, 2026.
- ^ Kemper, Jonathan (January 21, 2026). "Ollama brings local AI image generation to Mac". The Decoder. Retrieved May 22, 2026.
- ^ Lakshmanan, Ravie (January 29, 2026). "Researchers Find 175,000 Publicly Exposed Ollama AI Servers Across 130 Countries". The Hacker News. Retrieved April 29, 2026.